summaryrefslogtreecommitdiff
path: root/drivers/s390/crypto/vfio_ap_ops.c
blob: 118939a7729a1e46176e440a9975cc92642937da (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
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
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
// SPDX-License-Identifier: GPL-2.0+
/*
 * Adjunct processor matrix VFIO device driver callbacks.
 *
 * Copyright IBM Corp. 2018
 *
 * Author(s): Tony Krowiak <akrowiak@linux.ibm.com>
 *	      Halil Pasic <pasic@linux.ibm.com>
 *	      Pierre Morel <pmorel@linux.ibm.com>
 */
#include <linux/string.h>
#include <linux/vfio.h>
#include <linux/device.h>
#include <linux/list.h>
#include <linux/ctype.h>
#include <linux/bitops.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <asm/kvm.h>
#include <asm/zcrypt.h>

#include "vfio_ap_private.h"

#define VFIO_AP_MDEV_TYPE_HWVIRT "passthrough"
#define VFIO_AP_MDEV_NAME_HWVIRT "VFIO AP Passthrough Device"

static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev);
static struct vfio_ap_queue *vfio_ap_find_queue(int apqn);
static const struct vfio_device_ops vfio_ap_matrix_dev_ops;

static int match_apqn(struct device *dev, const void *data)
{
	struct vfio_ap_queue *q = dev_get_drvdata(dev);

	return (q->apqn == *(int *)(data)) ? 1 : 0;
}

/**
 * vfio_ap_get_queue - retrieve a queue with a specific APQN from a list
 * @matrix_mdev: the associated mediated matrix
 * @apqn: The queue APQN
 *
 * Retrieve a queue with a specific APQN from the list of the
 * devices of the vfio_ap_drv.
 * Verify that the APID and the APQI are set in the matrix.
 *
 * Return: the pointer to the associated vfio_ap_queue
 */
static struct vfio_ap_queue *vfio_ap_get_queue(
					struct ap_matrix_mdev *matrix_mdev,
					int apqn)
{
	struct vfio_ap_queue *q;

	if (!test_bit_inv(AP_QID_CARD(apqn), matrix_mdev->matrix.apm))
		return NULL;
	if (!test_bit_inv(AP_QID_QUEUE(apqn), matrix_mdev->matrix.aqm))
		return NULL;

	q = vfio_ap_find_queue(apqn);
	if (q)
		q->matrix_mdev = matrix_mdev;

	return q;
}

/**
 * vfio_ap_wait_for_irqclear - clears the IR bit or gives up after 5 tries
 * @apqn: The AP Queue number
 *
 * Checks the IRQ bit for the status of this APQN using ap_tapq.
 * Returns if the ap_tapq function succeeded and the bit is clear.
 * Returns if ap_tapq function failed with invalid, deconfigured or
 * checkstopped AP.
 * Otherwise retries up to 5 times after waiting 20ms.
 */
static void vfio_ap_wait_for_irqclear(int apqn)
{
	struct ap_queue_status status;
	int retry = 5;

	do {
		status = ap_tapq(apqn, NULL);
		switch (status.response_code) {
		case AP_RESPONSE_NORMAL:
		case AP_RESPONSE_RESET_IN_PROGRESS:
			if (!status.irq_enabled)
				return;
			fallthrough;
		case AP_RESPONSE_BUSY:
			msleep(20);
			break;
		case AP_RESPONSE_Q_NOT_AVAIL:
		case AP_RESPONSE_DECONFIGURED:
		case AP_RESPONSE_CHECKSTOPPED:
		default:
			WARN_ONCE(1, "%s: tapq rc %02x: %04x\n", __func__,
				  status.response_code, apqn);
			return;
		}
	} while (--retry);

	WARN_ONCE(1, "%s: tapq rc %02x: %04x could not clear IR bit\n",
		  __func__, status.response_code, apqn);
}

/**
 * vfio_ap_free_aqic_resources - free vfio_ap_queue resources
 * @q: The vfio_ap_queue
 *
 * Unregisters the ISC in the GIB when the saved ISC not invalid.
 * Unpins the guest's page holding the NIB when it exists.
 * Resets the saved_pfn and saved_isc to invalid values.
 */
static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q)
{
	if (!q)
		return;
	if (q->saved_isc != VFIO_AP_ISC_INVALID &&
	    !WARN_ON(!(q->matrix_mdev && q->matrix_mdev->kvm))) {
		kvm_s390_gisc_unregister(q->matrix_mdev->kvm, q->saved_isc);
		q->saved_isc = VFIO_AP_ISC_INVALID;
	}
	if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) {
		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev),
				 &q->saved_pfn, 1);
		q->saved_pfn = 0;
	}
}

/**
 * vfio_ap_irq_disable - disables and clears an ap_queue interrupt
 * @q: The vfio_ap_queue
 *
 * Uses ap_aqic to disable the interruption and in case of success, reset
 * in progress or IRQ disable command already proceeded: calls
 * vfio_ap_wait_for_irqclear() to check for the IRQ bit to be clear
 * and calls vfio_ap_free_aqic_resources() to free the resources associated
 * with the AP interrupt handling.
 *
 * In the case the AP is busy, or a reset is in progress,
 * retries after 20ms, up to 5 times.
 *
 * Returns if ap_aqic function failed with invalid, deconfigured or
 * checkstopped AP.
 *
 * Return: &struct ap_queue_status
 */
static struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q)
{
	struct ap_qirq_ctrl aqic_gisa = {};
	struct ap_queue_status status;
	int retries = 5;

	do {
		status = ap_aqic(q->apqn, aqic_gisa, NULL);
		switch (status.response_code) {
		case AP_RESPONSE_OTHERWISE_CHANGED:
		case AP_RESPONSE_NORMAL:
			vfio_ap_wait_for_irqclear(q->apqn);
			goto end_free;
		case AP_RESPONSE_RESET_IN_PROGRESS:
		case AP_RESPONSE_BUSY:
			msleep(20);
			break;
		case AP_RESPONSE_Q_NOT_AVAIL:
		case AP_RESPONSE_DECONFIGURED:
		case AP_RESPONSE_CHECKSTOPPED:
		case AP_RESPONSE_INVALID_ADDRESS:
		default:
			/* All cases in default means AP not operational */
			WARN_ONCE(1, "%s: ap_aqic status %d\n", __func__,
				  status.response_code);
			goto end_free;
		}
	} while (retries--);

	WARN_ONCE(1, "%s: ap_aqic status %d\n", __func__,
		  status.response_code);
end_free:
	vfio_ap_free_aqic_resources(q);
	q->matrix_mdev = NULL;
	return status;
}

/**
 * vfio_ap_irq_enable - Enable Interruption for a APQN
 *
 * @q:	 the vfio_ap_queue holding AQIC parameters
 *
 * Pin the NIB saved in *q
 * Register the guest ISC to GIB interface and retrieve the
 * host ISC to issue the host side PQAP/AQIC
 *
 * Response.status may be set to AP_RESPONSE_INVALID_ADDRESS in case the
 * vfio_pin_pages failed.
 *
 * Otherwise return the ap_queue_status returned by the ap_aqic(),
 * all retry handling will be done by the guest.
 *
 * Return: &struct ap_queue_status
 */
static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
						 int isc,
						 unsigned long nib)
{
	struct ap_qirq_ctrl aqic_gisa = {};
	struct ap_queue_status status = {};
	struct kvm_s390_gisa *gisa;
	struct kvm *kvm;
	unsigned long h_nib, g_pfn, h_pfn;
	int ret;

	g_pfn = nib >> PAGE_SHIFT;
	ret = vfio_pin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1,
			     IOMMU_READ | IOMMU_WRITE, &h_pfn);
	switch (ret) {
	case 1:
		break;
	default:
		status.response_code = AP_RESPONSE_INVALID_ADDRESS;
		return status;
	}

	kvm = q->matrix_mdev->kvm;
	gisa = kvm->arch.gisa_int.origin;

	h_nib = (h_pfn << PAGE_SHIFT) | (nib & ~PAGE_MASK);
	aqic_gisa.gisc = isc;
	aqic_gisa.isc = kvm_s390_gisc_register(kvm, isc);
	aqic_gisa.ir = 1;
	aqic_gisa.gisa = (uint64_t)gisa >> 4;

	status = ap_aqic(q->apqn, aqic_gisa, (void *)h_nib);
	switch (status.response_code) {
	case AP_RESPONSE_NORMAL:
		/* See if we did clear older IRQ configuration */
		vfio_ap_free_aqic_resources(q);
		q->saved_pfn = g_pfn;
		q->saved_isc = isc;
		break;
	case AP_RESPONSE_OTHERWISE_CHANGED:
		/* We could not modify IRQ setings: clear new configuration */
		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1);
		kvm_s390_gisc_unregister(kvm, isc);
		break;
	default:
		pr_warn("%s: apqn %04x: response: %02x\n", __func__, q->apqn,
			status.response_code);
		vfio_ap_irq_disable(q);
		break;
	}

	return status;
}

/**
 * handle_pqap - PQAP instruction callback
 *
 * @vcpu: The vcpu on which we received the PQAP instruction
 *
 * Get the general register contents to initialize internal variables.
 * REG[0]: APQN
 * REG[1]: IR and ISC
 * REG[2]: NIB
 *
 * Response.status may be set to following Response Code:
 * - AP_RESPONSE_Q_NOT_AVAIL: if the queue is not available
 * - AP_RESPONSE_DECONFIGURED: if the queue is not configured
 * - AP_RESPONSE_NORMAL (0) : in case of successs
 *   Check vfio_ap_setirq() and vfio_ap_clrirq() for other possible RC.
 * We take the matrix_dev lock to ensure serialization on queues and
 * mediated device access.
 *
 * Return: 0 if we could handle the request inside KVM.
 * Otherwise, returns -EOPNOTSUPP to let QEMU handle the fault.
 */
static int handle_pqap(struct kvm_vcpu *vcpu)
{
	uint64_t status;
	uint16_t apqn;
	struct vfio_ap_queue *q;
	struct ap_queue_status qstatus = {
			       .response_code = AP_RESPONSE_Q_NOT_AVAIL, };
	struct ap_matrix_mdev *matrix_mdev;

	/* If we do not use the AIV facility just go to userland */
	if (!(vcpu->arch.sie_block->eca & ECA_AIV))
		return -EOPNOTSUPP;

	apqn = vcpu->run->s.regs.gprs[0] & 0xffff;
	mutex_lock(&matrix_dev->lock);

	if (!vcpu->kvm->arch.crypto.pqap_hook)
		goto out_unlock;
	matrix_mdev = container_of(vcpu->kvm->arch.crypto.pqap_hook,
				   struct ap_matrix_mdev, pqap_hook);

	/* If the there is no guest using the mdev, there is nothing to do */
	if (!matrix_mdev->kvm)
		goto out_unlock;

	q = vfio_ap_get_queue(matrix_mdev, apqn);
	if (!q)
		goto out_unlock;

	status = vcpu->run->s.regs.gprs[1];

	/* If IR bit(16) is set we enable the interrupt */
	if ((status >> (63 - 16)) & 0x01)
		qstatus = vfio_ap_irq_enable(q, status & 0x07,
					     vcpu->run->s.regs.gprs[2]);
	else
		qstatus = vfio_ap_irq_disable(q);

out_unlock:
	memcpy(&vcpu->run->s.regs.gprs[1], &qstatus, sizeof(qstatus));
	vcpu->run->s.regs.gprs[1] >>= 32;
	mutex_unlock(&matrix_dev->lock);
	return 0;
}

static void vfio_ap_matrix_init(struct ap_config_info *info,
				struct ap_matrix *matrix)
{
	matrix->apm_max = info->apxa ? info->Na : 63;
	matrix->aqm_max = info->apxa ? info->Nd : 15;
	matrix->adm_max = info->apxa ? info->Nd : 15;
}

static int vfio_ap_mdev_probe(struct mdev_device *mdev)
{
	struct ap_matrix_mdev *matrix_mdev;
	int ret;

	if ((atomic_dec_if_positive(&matrix_dev->available_instances) < 0))
		return -EPERM;

	matrix_mdev = kzalloc(sizeof(*matrix_mdev), GFP_KERNEL);
	if (!matrix_mdev) {
		ret = -ENOMEM;
		goto err_dec_available;
	}
	vfio_init_group_dev(&matrix_mdev->vdev, &mdev->dev,
			    &vfio_ap_matrix_dev_ops);

	matrix_mdev->mdev = mdev;
	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->matrix);
	matrix_mdev->pqap_hook = handle_pqap;
	mutex_lock(&matrix_dev->lock);
	list_add(&matrix_mdev->node, &matrix_dev->mdev_list);
	mutex_unlock(&matrix_dev->lock);

	ret = vfio_register_group_dev(&matrix_mdev->vdev);
	if (ret)
		goto err_list;
	dev_set_drvdata(&mdev->dev, matrix_mdev);
	return 0;

err_list:
	mutex_lock(&matrix_dev->lock);
	list_del(&matrix_mdev->node);
	mutex_unlock(&matrix_dev->lock);
	kfree(matrix_mdev);
err_dec_available:
	atomic_inc(&matrix_dev->available_instances);
	return ret;
}

static void vfio_ap_mdev_remove(struct mdev_device *mdev)
{
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(&mdev->dev);

	vfio_unregister_group_dev(&matrix_mdev->vdev);

	mutex_lock(&matrix_dev->lock);
	vfio_ap_mdev_reset_queues(matrix_mdev);
	list_del(&matrix_mdev->node);
	kfree(matrix_mdev);
	atomic_inc(&matrix_dev->available_instances);
	mutex_unlock(&matrix_dev->lock);
}

static ssize_t name_show(struct mdev_type *mtype,
			 struct mdev_type_attribute *attr, char *buf)
{
	return sprintf(buf, "%s\n", VFIO_AP_MDEV_NAME_HWVIRT);
}

static MDEV_TYPE_ATTR_RO(name);

static ssize_t available_instances_show(struct mdev_type *mtype,
					struct mdev_type_attribute *attr,
					char *buf)
{
	return sprintf(buf, "%d\n",
		       atomic_read(&matrix_dev->available_instances));
}

static MDEV_TYPE_ATTR_RO(available_instances);

static ssize_t device_api_show(struct mdev_type *mtype,
			       struct mdev_type_attribute *attr, char *buf)
{
	return sprintf(buf, "%s\n", VFIO_DEVICE_API_AP_STRING);
}

static MDEV_TYPE_ATTR_RO(device_api);

static struct attribute *vfio_ap_mdev_type_attrs[] = {
	&mdev_type_attr_name.attr,
	&mdev_type_attr_device_api.attr,
	&mdev_type_attr_available_instances.attr,
	NULL,
};

static struct attribute_group vfio_ap_mdev_hwvirt_type_group = {
	.name = VFIO_AP_MDEV_TYPE_HWVIRT,
	.attrs = vfio_ap_mdev_type_attrs,
};

static struct attribute_group *vfio_ap_mdev_type_groups[] = {
	&vfio_ap_mdev_hwvirt_type_group,
	NULL,
};

struct vfio_ap_queue_reserved {
	unsigned long *apid;
	unsigned long *apqi;
	bool reserved;
};

/**
 * vfio_ap_has_queue - determines if the AP queue containing the target in @data
 *
 * @dev: an AP queue device
 * @data: a struct vfio_ap_queue_reserved reference
 *
 * Flags whether the AP queue device (@dev) has a queue ID containing the APQN,
 * apid or apqi specified in @data:
 *
 * - If @data contains both an apid and apqi value, then @data will be flagged
 *   as reserved if the APID and APQI fields for the AP queue device matches
 *
 * - If @data contains only an apid value, @data will be flagged as
 *   reserved if the APID field in the AP queue device matches
 *
 * - If @data contains only an apqi value, @data will be flagged as
 *   reserved if the APQI field in the AP queue device matches
 *
 * Return: 0 to indicate the input to function succeeded. Returns -EINVAL if
 * @data does not contain either an apid or apqi.
 */
static int vfio_ap_has_queue(struct device *dev, void *data)
{
	struct vfio_ap_queue_reserved *qres = data;
	struct ap_queue *ap_queue = to_ap_queue(dev);
	ap_qid_t qid;
	unsigned long id;

	if (qres->apid && qres->apqi) {
		qid = AP_MKQID(*qres->apid, *qres->apqi);
		if (qid == ap_queue->qid)
			qres->reserved = true;
	} else if (qres->apid && !qres->apqi) {
		id = AP_QID_CARD(ap_queue->qid);
		if (id == *qres->apid)
			qres->reserved = true;
	} else if (!qres->apid && qres->apqi) {
		id = AP_QID_QUEUE(ap_queue->qid);
		if (id == *qres->apqi)
			qres->reserved = true;
	} else {
		return -EINVAL;
	}

	return 0;
}

/**
 * vfio_ap_verify_queue_reserved - verifies that the AP queue containing
 * @apid or @aqpi is reserved
 *
 * @apid: an AP adapter ID
 * @apqi: an AP queue index
 *
 * Verifies that the AP queue with @apid/@apqi is reserved by the VFIO AP device
 * driver according to the following rules:
 *
 * - If both @apid and @apqi are not NULL, then there must be an AP queue
 *   device bound to the vfio_ap driver with the APQN identified by @apid and
 *   @apqi
 *
 * - If only @apid is not NULL, then there must be an AP queue device bound
 *   to the vfio_ap driver with an APQN containing @apid
 *
 * - If only @apqi is not NULL, then there must be an AP queue device bound
 *   to the vfio_ap driver with an APQN containing @apqi
 *
 * Return: 0 if the AP queue is reserved; otherwise, returns -EADDRNOTAVAIL.
 */
static int vfio_ap_verify_queue_reserved(unsigned long *apid,
					 unsigned long *apqi)
{
	int ret;
	struct vfio_ap_queue_reserved qres;

	qres.apid = apid;
	qres.apqi = apqi;
	qres.reserved = false;

	ret = driver_for_each_device(&matrix_dev->vfio_ap_drv->driver, NULL,
				     &qres, vfio_ap_has_queue);
	if (ret)
		return ret;

	if (qres.reserved)
		return 0;

	return -EADDRNOTAVAIL;
}

static int
vfio_ap_mdev_verify_queues_reserved_for_apid(struct ap_matrix_mdev *matrix_mdev,
					     unsigned long apid)
{
	int ret;
	unsigned long apqi;
	unsigned long nbits = matrix_mdev->matrix.aqm_max + 1;

	if (find_first_bit_inv(matrix_mdev->matrix.aqm, nbits) >= nbits)
		return vfio_ap_verify_queue_reserved(&apid, NULL);

	for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, nbits) {
		ret = vfio_ap_verify_queue_reserved(&apid, &apqi);
		if (ret)
			return ret;
	}

	return 0;
}

/**
 * vfio_ap_mdev_verify_no_sharing - verifies that the AP matrix is not configured
 *
 * @matrix_mdev: the mediated matrix device
 *
 * Verifies that the APQNs derived from the cross product of the AP adapter IDs
 * and AP queue indexes comprising the AP matrix are not configured for another
 * mediated device. AP queue sharing is not allowed.
 *
 * Return: 0 if the APQNs are not shared; otherwise returns -EADDRINUSE.
 */
static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev)
{
	struct ap_matrix_mdev *lstdev;
	DECLARE_BITMAP(apm, AP_DEVICES);
	DECLARE_BITMAP(aqm, AP_DOMAINS);

	list_for_each_entry(lstdev, &matrix_dev->mdev_list, node) {
		if (matrix_mdev == lstdev)
			continue;

		memset(apm, 0, sizeof(apm));
		memset(aqm, 0, sizeof(aqm));

		/*
		 * We work on full longs, as we can only exclude the leftover
		 * bits in non-inverse order. The leftover is all zeros.
		 */
		if (!bitmap_and(apm, matrix_mdev->matrix.apm,
				lstdev->matrix.apm, AP_DEVICES))
			continue;

		if (!bitmap_and(aqm, matrix_mdev->matrix.aqm,
				lstdev->matrix.aqm, AP_DOMAINS))
			continue;

		return -EADDRINUSE;
	}

	return 0;
}

/**
 * assign_adapter_store - parses the APID from @buf and sets the
 * corresponding bit in the mediated matrix device's APM
 *
 * @dev:	the matrix device
 * @attr:	the mediated matrix device's assign_adapter attribute
 * @buf:	a buffer containing the AP adapter number (APID) to
 *		be assigned
 * @count:	the number of bytes in @buf
 *
 * Return: the number of bytes processed if the APID is valid; otherwise,
 * returns one of the following errors:
 *
 *	1. -EINVAL
 *	   The APID is not a valid number
 *
 *	2. -ENODEV
 *	   The APID exceeds the maximum value configured for the system
 *
 *	3. -EADDRNOTAVAIL
 *	   An APQN derived from the cross product of the APID being assigned
 *	   and the APQIs previously assigned is not bound to the vfio_ap device
 *	   driver; or, if no APQIs have yet been assigned, the APID is not
 *	   contained in an APQN bound to the vfio_ap device driver.
 *
 *	4. -EADDRINUSE
 *	   An APQN derived from the cross product of the APID being assigned
 *	   and the APQIs previously assigned is being used by another mediated
 *	   matrix device
 */
static ssize_t assign_adapter_store(struct device *dev,
				    struct device_attribute *attr,
				    const char *buf, size_t count)
{
	int ret;
	unsigned long apid;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);

	mutex_lock(&matrix_dev->lock);

	/* If the KVM guest is running, disallow assignment of adapter */
	if (matrix_mdev->kvm) {
		ret = -EBUSY;
		goto done;
	}

	ret = kstrtoul(buf, 0, &apid);
	if (ret)
		goto done;

	if (apid > matrix_mdev->matrix.apm_max) {
		ret = -ENODEV;
		goto done;
	}

	/*
	 * Set the bit in the AP mask (APM) corresponding to the AP adapter
	 * number (APID). The bits in the mask, from most significant to least
	 * significant bit, correspond to APIDs 0-255.
	 */
	ret = vfio_ap_mdev_verify_queues_reserved_for_apid(matrix_mdev, apid);
	if (ret)
		goto done;

	set_bit_inv(apid, matrix_mdev->matrix.apm);

	ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev);
	if (ret)
		goto share_err;

	ret = count;
	goto done;

share_err:
	clear_bit_inv(apid, matrix_mdev->matrix.apm);
done:
	mutex_unlock(&matrix_dev->lock);

	return ret;
}
static DEVICE_ATTR_WO(assign_adapter);

/**
 * unassign_adapter_store - parses the APID from @buf and clears the
 * corresponding bit in the mediated matrix device's APM
 *
 * @dev:	the matrix device
 * @attr:	the mediated matrix device's unassign_adapter attribute
 * @buf:	a buffer containing the adapter number (APID) to be unassigned
 * @count:	the number of bytes in @buf
 *
 * Return: the number of bytes processed if the APID is valid; otherwise,
 * returns one of the following errors:
 *	-EINVAL if the APID is not a number
 *	-ENODEV if the APID it exceeds the maximum value configured for the
 *		system
 */
static ssize_t unassign_adapter_store(struct device *dev,
				      struct device_attribute *attr,
				      const char *buf, size_t count)
{
	int ret;
	unsigned long apid;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);

	mutex_lock(&matrix_dev->lock);

	/* If the KVM guest is running, disallow unassignment of adapter */
	if (matrix_mdev->kvm) {
		ret = -EBUSY;
		goto done;
	}

	ret = kstrtoul(buf, 0, &apid);
	if (ret)
		goto done;

	if (apid > matrix_mdev->matrix.apm_max) {
		ret = -ENODEV;
		goto done;
	}

	clear_bit_inv((unsigned long)apid, matrix_mdev->matrix.apm);
	ret = count;
done:
	mutex_unlock(&matrix_dev->lock);
	return ret;
}
static DEVICE_ATTR_WO(unassign_adapter);

static int
vfio_ap_mdev_verify_queues_reserved_for_apqi(struct ap_matrix_mdev *matrix_mdev,
					     unsigned long apqi)
{
	int ret;
	unsigned long apid;
	unsigned long nbits = matrix_mdev->matrix.apm_max + 1;

	if (find_first_bit_inv(matrix_mdev->matrix.apm, nbits) >= nbits)
		return vfio_ap_verify_queue_reserved(NULL, &apqi);

	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, nbits) {
		ret = vfio_ap_verify_queue_reserved(&apid, &apqi);
		if (ret)
			return ret;
	}

	return 0;
}

/**
 * assign_domain_store - parses the APQI from @buf and sets the
 * corresponding bit in the mediated matrix device's AQM
 *
 *
 * @dev:	the matrix device
 * @attr:	the mediated matrix device's assign_domain attribute
 * @buf:	a buffer containing the AP queue index (APQI) of the domain to
 *		be assigned
 * @count:	the number of bytes in @buf
 *
 * Return: the number of bytes processed if the APQI is valid; otherwise returns
 * one of the following errors:
 *
 *	1. -EINVAL
 *	   The APQI is not a valid number
 *
 *	2. -ENODEV
 *	   The APQI exceeds the maximum value configured for the system
 *
 *	3. -EADDRNOTAVAIL
 *	   An APQN derived from the cross product of the APQI being assigned
 *	   and the APIDs previously assigned is not bound to the vfio_ap device
 *	   driver; or, if no APIDs have yet been assigned, the APQI is not
 *	   contained in an APQN bound to the vfio_ap device driver.
 *
 *	4. -EADDRINUSE
 *	   An APQN derived from the cross product of the APQI being assigned
 *	   and the APIDs previously assigned is being used by another mediated
 *	   matrix device
 */
static ssize_t assign_domain_store(struct device *dev,
				   struct device_attribute *attr,
				   const char *buf, size_t count)
{
	int ret;
	unsigned long apqi;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
	unsigned long max_apqi = matrix_mdev->matrix.aqm_max;

	mutex_lock(&matrix_dev->lock);

	/* If the KVM guest is running, disallow assignment of domain */
	if (matrix_mdev->kvm) {
		ret = -EBUSY;
		goto done;
	}

	ret = kstrtoul(buf, 0, &apqi);
	if (ret)
		goto done;
	if (apqi > max_apqi) {
		ret = -ENODEV;
		goto done;
	}

	ret = vfio_ap_mdev_verify_queues_reserved_for_apqi(matrix_mdev, apqi);
	if (ret)
		goto done;

	set_bit_inv(apqi, matrix_mdev->matrix.aqm);

	ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev);
	if (ret)
		goto share_err;

	ret = count;
	goto done;

share_err:
	clear_bit_inv(apqi, matrix_mdev->matrix.aqm);
done:
	mutex_unlock(&matrix_dev->lock);

	return ret;
}
static DEVICE_ATTR_WO(assign_domain);


/**
 * unassign_domain_store - parses the APQI from @buf and clears the
 * corresponding bit in the mediated matrix device's AQM
 *
 * @dev:	the matrix device
 * @attr:	the mediated matrix device's unassign_domain attribute
 * @buf:	a buffer containing the AP queue index (APQI) of the domain to
 *		be unassigned
 * @count:	the number of bytes in @buf
 *
 * Return: the number of bytes processed if the APQI is valid; otherwise,
 * returns one of the following errors:
 *	-EINVAL if the APQI is not a number
 *	-ENODEV if the APQI exceeds the maximum value configured for the system
 */
static ssize_t unassign_domain_store(struct device *dev,
				     struct device_attribute *attr,
				     const char *buf, size_t count)
{
	int ret;
	unsigned long apqi;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);

	mutex_lock(&matrix_dev->lock);

	/* If the KVM guest is running, disallow unassignment of domain */
	if (matrix_mdev->kvm) {
		ret = -EBUSY;
		goto done;
	}

	ret = kstrtoul(buf, 0, &apqi);
	if (ret)
		goto done;

	if (apqi > matrix_mdev->matrix.aqm_max) {
		ret = -ENODEV;
		goto done;
	}

	clear_bit_inv((unsigned long)apqi, matrix_mdev->matrix.aqm);
	ret = count;

done:
	mutex_unlock(&matrix_dev->lock);
	return ret;
}
static DEVICE_ATTR_WO(unassign_domain);

/**
 * assign_control_domain_store - parses the domain ID from @buf and sets
 * the corresponding bit in the mediated matrix device's ADM
 *
 *
 * @dev:	the matrix device
 * @attr:	the mediated matrix device's assign_control_domain attribute
 * @buf:	a buffer containing the domain ID to be assigned
 * @count:	the number of bytes in @buf
 *
 * Return: the number of bytes processed if the domain ID is valid; otherwise,
 * returns one of the following errors:
 *	-EINVAL if the ID is not a number
 *	-ENODEV if the ID exceeds the maximum value configured for the system
 */
static ssize_t assign_control_domain_store(struct device *dev,
					   struct device_attribute *attr,
					   const char *buf, size_t count)
{
	int ret;
	unsigned long id;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);

	mutex_lock(&matrix_dev->lock);

	/* If the KVM guest is running, disallow assignment of control domain */
	if (matrix_mdev->kvm) {
		ret = -EBUSY;
		goto done;
	}

	ret = kstrtoul(buf, 0, &id);
	if (ret)
		goto done;

	if (id > matrix_mdev->matrix.adm_max) {
		ret = -ENODEV;
		goto done;
	}

	/* Set the bit in the ADM (bitmask) corresponding to the AP control
	 * domain number (id). The bits in the mask, from most significant to
	 * least significant, correspond to IDs 0 up to the one less than the
	 * number of control domains that can be assigned.
	 */
	set_bit_inv(id, matrix_mdev->matrix.adm);
	ret = count;
done:
	mutex_unlock(&matrix_dev->lock);
	return ret;
}
static DEVICE_ATTR_WO(assign_control_domain);

/**
 * unassign_control_domain_store - parses the domain ID from @buf and
 * clears the corresponding bit in the mediated matrix device's ADM
 *
 * @dev:	the matrix device
 * @attr:	the mediated matrix device's unassign_control_domain attribute
 * @buf:	a buffer containing the domain ID to be unassigned
 * @count:	the number of bytes in @buf
 *
 * Return: the number of bytes processed if the domain ID is valid; otherwise,
 * returns one of the following errors:
 *	-EINVAL if the ID is not a number
 *	-ENODEV if the ID exceeds the maximum value configured for the system
 */
static ssize_t unassign_control_domain_store(struct device *dev,
					     struct device_attribute *attr,
					     const char *buf, size_t count)
{
	int ret;
	unsigned long domid;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
	unsigned long max_domid =  matrix_mdev->matrix.adm_max;

	mutex_lock(&matrix_dev->lock);

	/* If a KVM guest is running, disallow unassignment of control domain */
	if (matrix_mdev->kvm) {
		ret = -EBUSY;
		goto done;
	}

	ret = kstrtoul(buf, 0, &domid);
	if (ret)
		goto done;
	if (domid > max_domid) {
		ret = -ENODEV;
		goto done;
	}

	clear_bit_inv(domid, matrix_mdev->matrix.adm);
	ret = count;
done:
	mutex_unlock(&matrix_dev->lock);
	return ret;
}
static DEVICE_ATTR_WO(unassign_control_domain);

static ssize_t control_domains_show(struct device *dev,
				    struct device_attribute *dev_attr,
				    char *buf)
{
	unsigned long id;
	int nchars = 0;
	int n;
	char *bufpos = buf;
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
	unsigned long max_domid = matrix_mdev->matrix.adm_max;

	mutex_lock(&matrix_dev->lock);
	for_each_set_bit_inv(id, matrix_mdev->matrix.adm, max_domid + 1) {
		n = sprintf(bufpos, "%04lx\n", id);
		bufpos += n;
		nchars += n;
	}
	mutex_unlock(&matrix_dev->lock);

	return nchars;
}
static DEVICE_ATTR_RO(control_domains);

static ssize_t matrix_show(struct device *dev, struct device_attribute *attr,
			   char *buf)
{
	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
	char *bufpos = buf;
	unsigned long apid;
	unsigned long apqi;
	unsigned long apid1;
	unsigned long apqi1;
	unsigned long napm_bits = matrix_mdev->matrix.apm_max + 1;
	unsigned long naqm_bits = matrix_mdev->matrix.aqm_max + 1;
	int nchars = 0;
	int n;

	apid1 = find_first_bit_inv(matrix_mdev->matrix.apm, napm_bits);
	apqi1 = find_first_bit_inv(matrix_mdev->matrix.aqm, naqm_bits);

	mutex_lock(&matrix_dev->lock);

	if ((apid1 < napm_bits) && (apqi1 < naqm_bits)) {
		for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, napm_bits) {
			for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm,
					     naqm_bits) {
				n = sprintf(bufpos, "%02lx.%04lx\n", apid,
					    apqi);
				bufpos += n;
				nchars += n;
			}
		}
	} else if (apid1 < napm_bits) {
		for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, napm_bits) {
			n = sprintf(bufpos, "%02lx.\n", apid);
			bufpos += n;
			nchars += n;
		}
	} else if (apqi1 < naqm_bits) {
		for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, naqm_bits) {
			n = sprintf(bufpos, ".%04lx\n", apqi);
			bufpos += n;
			nchars += n;
		}
	}

	mutex_unlock(&matrix_dev->lock);

	return nchars;
}
static DEVICE_ATTR_RO(matrix);

static struct attribute *vfio_ap_mdev_attrs[] = {
	&dev_attr_assign_adapter.attr,
	&dev_attr_unassign_adapter.attr,
	&dev_attr_assign_domain.attr,
	&dev_attr_unassign_domain.attr,
	&dev_attr_assign_control_domain.attr,
	&dev_attr_unassign_control_domain.attr,
	&dev_attr_control_domains.attr,
	&dev_attr_matrix.attr,
	NULL,
};

static struct attribute_group vfio_ap_mdev_attr_group = {
	.attrs = vfio_ap_mdev_attrs
};

static const struct attribute_group *vfio_ap_mdev_attr_groups[] = {
	&vfio_ap_mdev_attr_group,
	NULL
};

/**
 * vfio_ap_mdev_set_kvm - sets all data for @matrix_mdev that are needed
 * to manage AP resources for the guest whose state is represented by @kvm
 *
 * @matrix_mdev: a mediated matrix device
 * @kvm: reference to KVM instance
 *
 * Note: The matrix_dev->lock must be taken prior to calling
 * this function; however, the lock will be temporarily released while the
 * guest's AP configuration is set to avoid a potential lockdep splat.
 * The kvm->lock is taken to set the guest's AP configuration which, under
 * certain circumstances, will result in a circular lock dependency if this is
 * done under the @matrix_mdev->lock.
 *
 * Return: 0 if no other mediated matrix device has a reference to @kvm;
 * otherwise, returns an -EPERM.
 */
static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
				struct kvm *kvm)
{
	struct ap_matrix_mdev *m;

	if (kvm->arch.crypto.crycbd) {
		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
		up_write(&kvm->arch.crypto.pqap_hook_rwsem);

		mutex_lock(&kvm->lock);
		mutex_lock(&matrix_dev->lock);

		list_for_each_entry(m, &matrix_dev->mdev_list, node) {
			if (m != matrix_mdev && m->kvm == kvm) {
				mutex_unlock(&kvm->lock);
				mutex_unlock(&matrix_dev->lock);
				return -EPERM;
			}
		}

		kvm_get_kvm(kvm);
		matrix_mdev->kvm = kvm;
		kvm_arch_crypto_set_masks(kvm,
					  matrix_mdev->matrix.apm,
					  matrix_mdev->matrix.aqm,
					  matrix_mdev->matrix.adm);

		mutex_unlock(&kvm->lock);
		mutex_unlock(&matrix_dev->lock);
	}

	return 0;
}

/**
 * vfio_ap_mdev_iommu_notifier - IOMMU notifier callback
 *
 * @nb: The notifier block
 * @action: Action to be taken
 * @data: data associated with the request
 *
 * For an UNMAP request, unpin the guest IOVA (the NIB guest address we
 * pinned before). Other requests are ignored.
 *
 * Return: for an UNMAP request, NOFITY_OK; otherwise NOTIFY_DONE.
 */
static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
				       unsigned long action, void *data)
{
	struct ap_matrix_mdev *matrix_mdev;

	matrix_mdev = container_of(nb, struct ap_matrix_mdev, iommu_notifier);

	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
		struct vfio_iommu_type1_dma_unmap *unmap = data;
		unsigned long g_pfn = unmap->iova >> PAGE_SHIFT;

		vfio_unpin_pages(mdev_dev(matrix_mdev->mdev), &g_pfn, 1);
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

/**
 * vfio_ap_mdev_unset_kvm - performs clean-up of resources no longer needed
 * by @matrix_mdev.
 *
 * @matrix_mdev: a matrix mediated device
 *
 * Note: The matrix_dev->lock must be taken prior to calling
 * this function; however, the lock will be temporarily released while the
 * guest's AP configuration is cleared to avoid a potential lockdep splat.
 * The kvm->lock is taken to clear the guest's AP configuration which, under
 * certain circumstances, will result in a circular lock dependency if this is
 * done under the @matrix_mdev->lock.
 */
static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev,
				   struct kvm *kvm)
{
	if (kvm && kvm->arch.crypto.crycbd) {
		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
		kvm->arch.crypto.pqap_hook = NULL;
		up_write(&kvm->arch.crypto.pqap_hook_rwsem);

		mutex_lock(&kvm->lock);
		mutex_lock(&matrix_dev->lock);

		kvm_arch_crypto_clear_masks(kvm);
		vfio_ap_mdev_reset_queues(matrix_mdev);
		kvm_put_kvm(kvm);
		matrix_mdev->kvm = NULL;

		mutex_unlock(&kvm->lock);
		mutex_unlock(&matrix_dev->lock);
	}
}

static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
				       unsigned long action, void *data)
{
	int notify_rc = NOTIFY_OK;
	struct ap_matrix_mdev *matrix_mdev;

	if (action != VFIO_GROUP_NOTIFY_SET_KVM)
		return NOTIFY_OK;

	matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);

	if (!data)
		vfio_ap_mdev_unset_kvm(matrix_mdev, matrix_mdev->kvm);
	else if (vfio_ap_mdev_set_kvm(matrix_mdev, data))
		notify_rc = NOTIFY_DONE;

	return notify_rc;
}

static struct vfio_ap_queue *vfio_ap_find_queue(int apqn)
{
	struct device *dev;
	struct vfio_ap_queue *q = NULL;

	dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL,
				 &apqn, match_apqn);
	if (dev) {
		q = dev_get_drvdata(dev);
		put_device(dev);
	}

	return q;
}

int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q,
			     unsigned int retry)
{
	struct ap_queue_status status;
	int ret;
	int retry2 = 2;

	if (!q)
		return 0;

retry_zapq:
	status = ap_zapq(q->apqn);
	switch (status.response_code) {
	case AP_RESPONSE_NORMAL:
		ret = 0;
		break;
	case AP_RESPONSE_RESET_IN_PROGRESS:
		if (retry--) {
			msleep(20);
			goto retry_zapq;
		}
		ret = -EBUSY;
		break;
	case AP_RESPONSE_Q_NOT_AVAIL:
	case AP_RESPONSE_DECONFIGURED:
	case AP_RESPONSE_CHECKSTOPPED:
		WARN_ON_ONCE(status.irq_enabled);
		ret = -EBUSY;
		goto free_resources;
	default:
		/* things are really broken, give up */
		WARN(true, "PQAP/ZAPQ completed with invalid rc (%x)\n",
		     status.response_code);
		return -EIO;
	}

	/* wait for the reset to take effect */
	while (retry2--) {
		if (status.queue_empty && !status.irq_enabled)
			break;
		msleep(20);
		status = ap_tapq(q->apqn, NULL);
	}
	WARN_ON_ONCE(retry2 <= 0);

free_resources:
	vfio_ap_free_aqic_resources(q);

	return ret;
}

static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev)
{
	int ret;
	int rc = 0;
	unsigned long apid, apqi;
	struct vfio_ap_queue *q;

	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm,
			     matrix_mdev->matrix.apm_max + 1) {
		for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm,
				     matrix_mdev->matrix.aqm_max + 1) {
			q = vfio_ap_find_queue(AP_MKQID(apid, apqi));
			ret = vfio_ap_mdev_reset_queue(q, 1);
			/*
			 * Regardless whether a queue turns out to be busy, or
			 * is not operational, we need to continue resetting
			 * the remaining queues.
			 */
			if (ret)
				rc = ret;
		}
	}

	return rc;
}

static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
{
	struct ap_matrix_mdev *matrix_mdev =
		container_of(vdev, struct ap_matrix_mdev, vdev);
	unsigned long events;
	int ret;

	matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier;
	events = VFIO_GROUP_NOTIFY_SET_KVM;

	ret = vfio_register_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
				     &events, &matrix_mdev->group_notifier);
	if (ret)
		return ret;

	matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier;
	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
				     &events, &matrix_mdev->iommu_notifier);
	if (ret)
		goto out_unregister_group;
	return 0;

out_unregister_group:
	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
				 &matrix_mdev->group_notifier);
	return ret;
}

static void vfio_ap_mdev_close_device(struct vfio_device *vdev)
{
	struct ap_matrix_mdev *matrix_mdev =
		container_of(vdev, struct ap_matrix_mdev, vdev);

	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
				 &matrix_mdev->iommu_notifier);
	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
				 &matrix_mdev->group_notifier);
	vfio_ap_mdev_unset_kvm(matrix_mdev, matrix_mdev->kvm);
}

static int vfio_ap_mdev_get_device_info(unsigned long arg)
{
	unsigned long minsz;
	struct vfio_device_info info;

	minsz = offsetofend(struct vfio_device_info, num_irqs);

	if (copy_from_user(&info, (void __user *)arg, minsz))
		return -EFAULT;

	if (info.argsz < minsz)
		return -EINVAL;

	info.flags = VFIO_DEVICE_FLAGS_AP | VFIO_DEVICE_FLAGS_RESET;
	info.num_regions = 0;
	info.num_irqs = 0;

	return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
}

static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev,
				    unsigned int cmd, unsigned long arg)
{
	struct ap_matrix_mdev *matrix_mdev =
		container_of(vdev, struct ap_matrix_mdev, vdev);
	int ret;

	mutex_lock(&matrix_dev->lock);
	switch (cmd) {
	case VFIO_DEVICE_GET_INFO:
		ret = vfio_ap_mdev_get_device_info(arg);
		break;
	case VFIO_DEVICE_RESET:
		ret = vfio_ap_mdev_reset_queues(matrix_mdev);
		break;
	default:
		ret = -EOPNOTSUPP;
		break;
	}
	mutex_unlock(&matrix_dev->lock);

	return ret;
}

static const struct vfio_device_ops vfio_ap_matrix_dev_ops = {
	.open_device = vfio_ap_mdev_open_device,
	.close_device = vfio_ap_mdev_close_device,
	.ioctl = vfio_ap_mdev_ioctl,
};

static struct mdev_driver vfio_ap_matrix_driver = {
	.driver = {
		.name = "vfio_ap_mdev",
		.owner = THIS_MODULE,
		.mod_name = KBUILD_MODNAME,
		.dev_groups = vfio_ap_mdev_attr_groups,
	},
	.probe = vfio_ap_mdev_probe,
	.remove = vfio_ap_mdev_remove,
};

static const struct mdev_parent_ops vfio_ap_matrix_ops = {
	.owner			= THIS_MODULE,
	.device_driver		= &vfio_ap_matrix_driver,
	.supported_type_groups	= vfio_ap_mdev_type_groups,
};

int vfio_ap_mdev_register(void)
{
	int ret;

	atomic_set(&matrix_dev->available_instances, MAX_ZDEV_ENTRIES_EXT);

	ret = mdev_register_driver(&vfio_ap_matrix_driver);
	if (ret)
		return ret;

	ret = mdev_register_device(&matrix_dev->device, &vfio_ap_matrix_ops);
	if (ret)
		goto err_driver;
	return 0;

err_driver:
	mdev_unregister_driver(&vfio_ap_matrix_driver);
	return ret;
}

void vfio_ap_mdev_unregister(void)
{
	mdev_unregister_device(&matrix_dev->device);
	mdev_unregister_driver(&vfio_ap_matrix_driver);
}