Linux Audio

Check our new training course

Embedded Linux Audio

Check our new training course
with Creative Commons CC-BY-SA
lecture materials

Bootlin logo

Elixir Cross Referencer

Loading...
   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
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
/*
 * KVMGT - the implementation of Intel mediated pass-through framework for KVM
 *
 * Copyright(c) 2014-2016 Intel Corporation. All rights reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 * Authors:
 *    Kevin Tian <kevin.tian@intel.com>
 *    Jike Song <jike.song@intel.com>
 *    Xiaoguang Chen <xiaoguang.chen@intel.com>
 */

#include <linux/init.h>
#include <linux/device.h>
#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/types.h>
#include <linux/list.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <linux/uuid.h>
#include <linux/kvm_host.h>
#include <linux/vfio.h>
#include <linux/mdev.h>

#include "i915_drv.h"
#include "gvt.h"

static const struct intel_gvt_ops *intel_gvt_ops;

/* helper macros copied from vfio-pci */
#define VFIO_PCI_OFFSET_SHIFT   40
#define VFIO_PCI_OFFSET_TO_INDEX(off)   (off >> VFIO_PCI_OFFSET_SHIFT)
#define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT)
#define VFIO_PCI_OFFSET_MASK    (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1)

struct vfio_region {
	u32				type;
	u32				subtype;
	size_t				size;
	u32				flags;
};

struct kvmgt_pgfn {
	gfn_t gfn;
	struct hlist_node hnode;
};

struct kvmgt_guest_info {
	struct kvm *kvm;
	struct intel_vgpu *vgpu;
	struct kvm_page_track_notifier_node track_node;
#define NR_BKT (1 << 18)
	struct hlist_head ptable[NR_BKT];
#undef NR_BKT
};

struct gvt_dma {
	struct rb_node node;
	gfn_t gfn;
	unsigned long iova;
};

static inline bool handle_valid(unsigned long handle)
{
	return !!(handle & ~0xff);
}

static int kvmgt_guest_init(struct mdev_device *mdev);
static void intel_vgpu_release_work(struct work_struct *work);
static bool kvmgt_guest_exit(struct kvmgt_guest_info *info);

static int gvt_dma_map_iova(struct intel_vgpu *vgpu, kvm_pfn_t pfn,
		unsigned long *iova)
{
	struct page *page;
	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
	dma_addr_t daddr;

	if (unlikely(!pfn_valid(pfn)))
		return -EFAULT;

	page = pfn_to_page(pfn);
	daddr = dma_map_page(dev, page, 0, PAGE_SIZE,
			PCI_DMA_BIDIRECTIONAL);
	if (dma_mapping_error(dev, daddr))
		return -ENOMEM;

	*iova = (unsigned long)(daddr >> PAGE_SHIFT);
	return 0;
}

static void gvt_dma_unmap_iova(struct intel_vgpu *vgpu, unsigned long iova)
{
	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
	dma_addr_t daddr;

	daddr = (dma_addr_t)(iova << PAGE_SHIFT);
	dma_unmap_page(dev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
}

static struct gvt_dma *__gvt_cache_find(struct intel_vgpu *vgpu, gfn_t gfn)
{
	struct rb_node *node = vgpu->vdev.cache.rb_node;
	struct gvt_dma *ret = NULL;

	while (node) {
		struct gvt_dma *itr = rb_entry(node, struct gvt_dma, node);

		if (gfn < itr->gfn)
			node = node->rb_left;
		else if (gfn > itr->gfn)
			node = node->rb_right;
		else {
			ret = itr;
			goto out;
		}
	}

out:
	return ret;
}

static unsigned long gvt_cache_find(struct intel_vgpu *vgpu, gfn_t gfn)
{
	struct gvt_dma *entry;
	unsigned long iova;

	mutex_lock(&vgpu->vdev.cache_lock);

	entry = __gvt_cache_find(vgpu, gfn);
	iova = (entry == NULL) ? INTEL_GVT_INVALID_ADDR : entry->iova;

	mutex_unlock(&vgpu->vdev.cache_lock);
	return iova;
}

static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
		unsigned long iova)
{
	struct gvt_dma *new, *itr;
	struct rb_node **link = &vgpu->vdev.cache.rb_node, *parent = NULL;

	new = kzalloc(sizeof(struct gvt_dma), GFP_KERNEL);
	if (!new)
		return;

	new->gfn = gfn;
	new->iova = iova;

	mutex_lock(&vgpu->vdev.cache_lock);
	while (*link) {
		parent = *link;
		itr = rb_entry(parent, struct gvt_dma, node);

		if (gfn == itr->gfn)
			goto out;
		else if (gfn < itr->gfn)
			link = &parent->rb_left;
		else
			link = &parent->rb_right;
	}

	rb_link_node(&new->node, parent, link);
	rb_insert_color(&new->node, &vgpu->vdev.cache);
	mutex_unlock(&vgpu->vdev.cache_lock);
	return;

out:
	mutex_unlock(&vgpu->vdev.cache_lock);
	kfree(new);
}

static void __gvt_cache_remove_entry(struct intel_vgpu *vgpu,
				struct gvt_dma *entry)
{
	rb_erase(&entry->node, &vgpu->vdev.cache);
	kfree(entry);
}

static void gvt_cache_remove(struct intel_vgpu *vgpu, gfn_t gfn)
{
	struct device *dev = mdev_dev(vgpu->vdev.mdev);
	struct gvt_dma *this;
	unsigned long g1;
	int rc;

	mutex_lock(&vgpu->vdev.cache_lock);
	this  = __gvt_cache_find(vgpu, gfn);
	if (!this) {
		mutex_unlock(&vgpu->vdev.cache_lock);
		return;
	}

	g1 = gfn;
	gvt_dma_unmap_iova(vgpu, this->iova);
	rc = vfio_unpin_pages(dev, &g1, 1);
	WARN_ON(rc != 1);
	__gvt_cache_remove_entry(vgpu, this);
	mutex_unlock(&vgpu->vdev.cache_lock);
}

static void gvt_cache_init(struct intel_vgpu *vgpu)
{
	vgpu->vdev.cache = RB_ROOT;
	mutex_init(&vgpu->vdev.cache_lock);
}

static void gvt_cache_destroy(struct intel_vgpu *vgpu)
{
	struct gvt_dma *dma;
	struct rb_node *node = NULL;
	struct device *dev = mdev_dev(vgpu->vdev.mdev);
	unsigned long gfn;

	for (;;) {
		mutex_lock(&vgpu->vdev.cache_lock);
		node = rb_first(&vgpu->vdev.cache);
		if (!node) {
			mutex_unlock(&vgpu->vdev.cache_lock);
			break;
		}
		dma = rb_entry(node, struct gvt_dma, node);
		gvt_dma_unmap_iova(vgpu, dma->iova);
		gfn = dma->gfn;
		__gvt_cache_remove_entry(vgpu, dma);
		mutex_unlock(&vgpu->vdev.cache_lock);
		vfio_unpin_pages(dev, &gfn, 1);
	}
}

static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt,
		const char *name)
{
	int i;
	struct intel_vgpu_type *t;
	const char *driver_name = dev_driver_string(
			&gvt->dev_priv->drm.pdev->dev);

	for (i = 0; i < gvt->num_types; i++) {
		t = &gvt->types[i];
		if (!strncmp(t->name, name + strlen(driver_name) + 1,
			sizeof(t->name)))
			return t;
	}

	return NULL;
}

static ssize_t available_instances_show(struct kobject *kobj,
					struct device *dev, char *buf)
{
	struct intel_vgpu_type *type;
	unsigned int num = 0;
	void *gvt = kdev_to_i915(dev)->gvt;

	type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
	if (!type)
		num = 0;
	else
		num = type->avail_instance;

	return sprintf(buf, "%u\n", num);
}

static ssize_t device_api_show(struct kobject *kobj, struct device *dev,
		char *buf)
{
	return sprintf(buf, "%s\n", VFIO_DEVICE_API_PCI_STRING);
}

static ssize_t description_show(struct kobject *kobj, struct device *dev,
		char *buf)
{
	struct intel_vgpu_type *type;
	void *gvt = kdev_to_i915(dev)->gvt;

	type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
	if (!type)
		return 0;

	return sprintf(buf, "low_gm_size: %dMB\nhigh_gm_size: %dMB\n"
		       "fence: %d\nresolution: %s\n"
		       "weight: %d\n",
		       BYTES_TO_MB(type->low_gm_size),
		       BYTES_TO_MB(type->high_gm_size),
		       type->fence, vgpu_edid_str(type->resolution),
		       type->weight);
}

static MDEV_TYPE_ATTR_RO(available_instances);
static MDEV_TYPE_ATTR_RO(device_api);
static MDEV_TYPE_ATTR_RO(description);

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

static struct attribute_group *intel_vgpu_type_groups[] = {
	[0 ... NR_MAX_INTEL_VGPU_TYPES - 1] = NULL,
};

static bool intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt)
{
	int i, j;
	struct intel_vgpu_type *type;
	struct attribute_group *group;

	for (i = 0; i < gvt->num_types; i++) {
		type = &gvt->types[i];

		group = kzalloc(sizeof(struct attribute_group), GFP_KERNEL);
		if (WARN_ON(!group))
			goto unwind;

		group->name = type->name;
		group->attrs = type_attrs;
		intel_vgpu_type_groups[i] = group;
	}

	return true;

unwind:
	for (j = 0; j < i; j++) {
		group = intel_vgpu_type_groups[j];
		kfree(group);
	}

	return false;
}

static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt)
{
	int i;
	struct attribute_group *group;

	for (i = 0; i < gvt->num_types; i++) {
		group = intel_vgpu_type_groups[i];
		kfree(group);
	}
}

static void kvmgt_protect_table_init(struct kvmgt_guest_info *info)
{
	hash_init(info->ptable);
}

static void kvmgt_protect_table_destroy(struct kvmgt_guest_info *info)
{
	struct kvmgt_pgfn *p;
	struct hlist_node *tmp;
	int i;

	hash_for_each_safe(info->ptable, i, tmp, p, hnode) {
		hash_del(&p->hnode);
		kfree(p);
	}
}

static struct kvmgt_pgfn *
__kvmgt_protect_table_find(struct kvmgt_guest_info *info, gfn_t gfn)
{
	struct kvmgt_pgfn *p, *res = NULL;

	hash_for_each_possible(info->ptable, p, hnode, gfn) {
		if (gfn == p->gfn) {
			res = p;
			break;
		}
	}

	return res;
}

static bool kvmgt_gfn_is_write_protected(struct kvmgt_guest_info *info,
				gfn_t gfn)
{
	struct kvmgt_pgfn *p;

	p = __kvmgt_protect_table_find(info, gfn);
	return !!p;
}

static void kvmgt_protect_table_add(struct kvmgt_guest_info *info, gfn_t gfn)
{
	struct kvmgt_pgfn *p;

	if (kvmgt_gfn_is_write_protected(info, gfn))
		return;

	p = kzalloc(sizeof(struct kvmgt_pgfn), GFP_ATOMIC);
	if (WARN(!p, "gfn: 0x%llx\n", gfn))
		return;

	p->gfn = gfn;
	hash_add(info->ptable, &p->hnode, gfn);
}

static void kvmgt_protect_table_del(struct kvmgt_guest_info *info,
				gfn_t gfn)
{
	struct kvmgt_pgfn *p;

	p = __kvmgt_protect_table_find(info, gfn);
	if (p) {
		hash_del(&p->hnode);
		kfree(p);
	}
}

static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
{
	struct intel_vgpu *vgpu = NULL;
	struct intel_vgpu_type *type;
	struct device *pdev;
	void *gvt;
	int ret;

	pdev = mdev_parent_dev(mdev);
	gvt = kdev_to_i915(pdev)->gvt;

	type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
	if (!type) {
		gvt_vgpu_err("failed to find type %s to create\n",
						kobject_name(kobj));
		ret = -EINVAL;
		goto out;
	}

	vgpu = intel_gvt_ops->vgpu_create(gvt, type);
	if (IS_ERR_OR_NULL(vgpu)) {
		ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu);
		gvt_vgpu_err("failed to create intel vgpu: %d\n", ret);
		goto out;
	}

	INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work);

	vgpu->vdev.mdev = mdev;
	mdev_set_drvdata(mdev, vgpu);

	gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n",
		     dev_name(mdev_dev(mdev)));
	ret = 0;

out:
	return ret;
}

static int intel_vgpu_remove(struct mdev_device *mdev)
{
	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);

	if (handle_valid(vgpu->handle))
		return -EBUSY;

	intel_gvt_ops->vgpu_destroy(vgpu);
	return 0;
}

static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
				     unsigned long action, void *data)
{
	struct intel_vgpu *vgpu = container_of(nb,
					struct intel_vgpu,
					vdev.iommu_notifier);

	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
		struct vfio_iommu_type1_dma_unmap *unmap = data;
		unsigned long gfn, end_gfn;

		gfn = unmap->iova >> PAGE_SHIFT;
		end_gfn = gfn + unmap->size / PAGE_SIZE;

		while (gfn < end_gfn)
			gvt_cache_remove(vgpu, gfn++);
	}

	return NOTIFY_OK;
}

static int intel_vgpu_group_notifier(struct notifier_block *nb,
				     unsigned long action, void *data)
{
	struct intel_vgpu *vgpu = container_of(nb,
					struct intel_vgpu,
					vdev.group_notifier);

	/* the only action we care about */
	if (action == VFIO_GROUP_NOTIFY_SET_KVM) {
		vgpu->vdev.kvm = data;

		if (!data)
			schedule_work(&vgpu->vdev.release_work);
	}

	return NOTIFY_OK;
}

static int intel_vgpu_open(struct mdev_device *mdev)
{
	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
	unsigned long events;
	int ret;

	vgpu->vdev.iommu_notifier.notifier_call = intel_vgpu_iommu_notifier;
	vgpu->vdev.group_notifier.notifier_call = intel_vgpu_group_notifier;

	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &events,
				&vgpu->vdev.iommu_notifier);
	if (ret != 0) {
		gvt_vgpu_err("vfio_register_notifier for iommu failed: %d\n",
			ret);
		goto out;
	}

	events = VFIO_GROUP_NOTIFY_SET_KVM;
	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &events,
				&vgpu->vdev.group_notifier);
	if (ret != 0) {
		gvt_vgpu_err("vfio_register_notifier for group failed: %d\n",
			ret);
		goto undo_iommu;
	}

	ret = kvmgt_guest_init(mdev);
	if (ret)
		goto undo_group;

	intel_gvt_ops->vgpu_activate(vgpu);

	atomic_set(&vgpu->vdev.released, 0);
	return ret;

undo_group:
	vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY,
					&vgpu->vdev.group_notifier);

undo_iommu:
	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
					&vgpu->vdev.iommu_notifier);
out:
	return ret;
}

static void __intel_vgpu_release(struct intel_vgpu *vgpu)
{
	struct kvmgt_guest_info *info;
	int ret;

	if (!handle_valid(vgpu->handle))
		return;

	if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
		return;

	intel_gvt_ops->vgpu_deactivate(vgpu);

	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
					&vgpu->vdev.iommu_notifier);
	WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);

	ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_GROUP_NOTIFY,
					&vgpu->vdev.group_notifier);
	WARN(ret, "vfio_unregister_notifier for group failed: %d\n", ret);

	info = (struct kvmgt_guest_info *)vgpu->handle;
	kvmgt_guest_exit(info);

	vgpu->vdev.kvm = NULL;
	vgpu->handle = 0;
}

static void intel_vgpu_release(struct mdev_device *mdev)
{
	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);

	__intel_vgpu_release(vgpu);
}

static void intel_vgpu_release_work(struct work_struct *work)
{
	struct intel_vgpu *vgpu = container_of(work, struct intel_vgpu,
					vdev.release_work);

	__intel_vgpu_release(vgpu);
}

static uint64_t intel_vgpu_get_bar0_addr(struct intel_vgpu *vgpu)
{
	u32 start_lo, start_hi;
	u32 mem_type;
	int pos = PCI_BASE_ADDRESS_0;

	start_lo = (*(u32 *)(vgpu->cfg_space.virtual_cfg_space + pos)) &
			PCI_BASE_ADDRESS_MEM_MASK;
	mem_type = (*(u32 *)(vgpu->cfg_space.virtual_cfg_space + pos)) &
			PCI_BASE_ADDRESS_MEM_TYPE_MASK;

	switch (mem_type) {
	case PCI_BASE_ADDRESS_MEM_TYPE_64:
		start_hi = (*(u32 *)(vgpu->cfg_space.virtual_cfg_space
						+ pos + 4));
		break;
	case PCI_BASE_ADDRESS_MEM_TYPE_32:
	case PCI_BASE_ADDRESS_MEM_TYPE_1M:
		/* 1M mem BAR treated as 32-bit BAR */
	default:
		/* mem unknown type treated as 32-bit BAR */
		start_hi = 0;
		break;
	}

	return ((u64)start_hi << 32) | start_lo;
}

static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
			size_t count, loff_t *ppos, bool is_write)
{
	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	uint64_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
	int ret = -EINVAL;


	if (index >= VFIO_PCI_NUM_REGIONS) {
		gvt_vgpu_err("invalid index: %u\n", index);
		return -EINVAL;
	}

	switch (index) {
	case VFIO_PCI_CONFIG_REGION_INDEX:
		if (is_write)
			ret = intel_gvt_ops->emulate_cfg_write(vgpu, pos,
						buf, count);
		else
			ret = intel_gvt_ops->emulate_cfg_read(vgpu, pos,
						buf, count);
		break;
	case VFIO_PCI_BAR0_REGION_INDEX:
	case VFIO_PCI_BAR1_REGION_INDEX:
		if (is_write) {
			uint64_t bar0_start = intel_vgpu_get_bar0_addr(vgpu);

			ret = intel_gvt_ops->emulate_mmio_write(vgpu,
						bar0_start + pos, buf, count);
		} else {
			uint64_t bar0_start = intel_vgpu_get_bar0_addr(vgpu);

			ret = intel_gvt_ops->emulate_mmio_read(vgpu,
						bar0_start + pos, buf, count);
		}
		break;
	case VFIO_PCI_BAR2_REGION_INDEX:
	case VFIO_PCI_BAR3_REGION_INDEX:
	case VFIO_PCI_BAR4_REGION_INDEX:
	case VFIO_PCI_BAR5_REGION_INDEX:
	case VFIO_PCI_VGA_REGION_INDEX:
	case VFIO_PCI_ROM_REGION_INDEX:
	default:
		gvt_vgpu_err("unsupported region: %u\n", index);
	}

	return ret == 0 ? count : ret;
}

static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf,
			size_t count, loff_t *ppos)
{
	unsigned int done = 0;
	int ret;

	while (count) {
		size_t filled;

		if (count >= 4 && !(*ppos % 4)) {
			u32 val;

			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
					ppos, false);
			if (ret <= 0)
				goto read_err;

			if (copy_to_user(buf, &val, sizeof(val)))
				goto read_err;

			filled = 4;
		} else if (count >= 2 && !(*ppos % 2)) {
			u16 val;

			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
					ppos, false);
			if (ret <= 0)
				goto read_err;

			if (copy_to_user(buf, &val, sizeof(val)))
				goto read_err;

			filled = 2;
		} else {
			u8 val;

			ret = intel_vgpu_rw(mdev, &val, sizeof(val), ppos,
					false);
			if (ret <= 0)
				goto read_err;

			if (copy_to_user(buf, &val, sizeof(val)))
				goto read_err;

			filled = 1;
		}

		count -= filled;
		done += filled;
		*ppos += filled;
		buf += filled;
	}

	return done;

read_err:
	return -EFAULT;
}

static ssize_t intel_vgpu_write(struct mdev_device *mdev,
				const char __user *buf,
				size_t count, loff_t *ppos)
{
	unsigned int done = 0;
	int ret;

	while (count) {
		size_t filled;

		if (count >= 4 && !(*ppos % 4)) {
			u32 val;

			if (copy_from_user(&val, buf, sizeof(val)))
				goto write_err;

			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
					ppos, true);
			if (ret <= 0)
				goto write_err;

			filled = 4;
		} else if (count >= 2 && !(*ppos % 2)) {
			u16 val;

			if (copy_from_user(&val, buf, sizeof(val)))
				goto write_err;

			ret = intel_vgpu_rw(mdev, (char *)&val,
					sizeof(val), ppos, true);
			if (ret <= 0)
				goto write_err;

			filled = 2;
		} else {
			u8 val;

			if (copy_from_user(&val, buf, sizeof(val)))
				goto write_err;

			ret = intel_vgpu_rw(mdev, &val, sizeof(val),
					ppos, true);
			if (ret <= 0)
				goto write_err;

			filled = 1;
		}

		count -= filled;
		done += filled;
		*ppos += filled;
		buf += filled;
	}

	return done;
write_err:
	return -EFAULT;
}

static int intel_vgpu_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
{
	unsigned int index;
	u64 virtaddr;
	unsigned long req_size, pgoff = 0;
	pgprot_t pg_prot;
	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);

	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
	if (index >= VFIO_PCI_ROM_REGION_INDEX)
		return -EINVAL;

	if (vma->vm_end < vma->vm_start)
		return -EINVAL;
	if ((vma->vm_flags & VM_SHARED) == 0)
		return -EINVAL;
	if (index != VFIO_PCI_BAR2_REGION_INDEX)
		return -EINVAL;

	pg_prot = vma->vm_page_prot;
	virtaddr = vma->vm_start;
	req_size = vma->vm_end - vma->vm_start;
	pgoff = vgpu_aperture_pa_base(vgpu) >> PAGE_SHIFT;

	return remap_pfn_range(vma, virtaddr, pgoff, req_size, pg_prot);
}

static int intel_vgpu_get_irq_count(struct intel_vgpu *vgpu, int type)
{
	if (type == VFIO_PCI_INTX_IRQ_INDEX || type == VFIO_PCI_MSI_IRQ_INDEX)
		return 1;

	return 0;
}

static int intel_vgpu_set_intx_mask(struct intel_vgpu *vgpu,
			unsigned int index, unsigned int start,
			unsigned int count, uint32_t flags,
			void *data)
{
	return 0;
}

static int intel_vgpu_set_intx_unmask(struct intel_vgpu *vgpu,
			unsigned int index, unsigned int start,
			unsigned int count, uint32_t flags, void *data)
{
	return 0;
}

static int intel_vgpu_set_intx_trigger(struct intel_vgpu *vgpu,
		unsigned int index, unsigned int start, unsigned int count,
		uint32_t flags, void *data)
{
	return 0;
}

static int intel_vgpu_set_msi_trigger(struct intel_vgpu *vgpu,
		unsigned int index, unsigned int start, unsigned int count,
		uint32_t flags, void *data)
{
	struct eventfd_ctx *trigger;

	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
		int fd = *(int *)data;

		trigger = eventfd_ctx_fdget(fd);
		if (IS_ERR(trigger)) {
			gvt_vgpu_err("eventfd_ctx_fdget failed\n");
			return PTR_ERR(trigger);
		}
		vgpu->vdev.msi_trigger = trigger;
	}

	return 0;
}

static int intel_vgpu_set_irqs(struct intel_vgpu *vgpu, uint32_t flags,
		unsigned int index, unsigned int start, unsigned int count,
		void *data)
{
	int (*func)(struct intel_vgpu *vgpu, unsigned int index,
			unsigned int start, unsigned int count, uint32_t flags,
			void *data) = NULL;

	switch (index) {
	case VFIO_PCI_INTX_IRQ_INDEX:
		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
		case VFIO_IRQ_SET_ACTION_MASK:
			func = intel_vgpu_set_intx_mask;
			break;
		case VFIO_IRQ_SET_ACTION_UNMASK:
			func = intel_vgpu_set_intx_unmask;
			break;
		case VFIO_IRQ_SET_ACTION_TRIGGER:
			func = intel_vgpu_set_intx_trigger;
			break;
		}
		break;
	case VFIO_PCI_MSI_IRQ_INDEX:
		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
		case VFIO_IRQ_SET_ACTION_MASK:
		case VFIO_IRQ_SET_ACTION_UNMASK:
			/* XXX Need masking support exported */
			break;
		case VFIO_IRQ_SET_ACTION_TRIGGER:
			func = intel_vgpu_set_msi_trigger;
			break;
		}
		break;
	}

	if (!func)
		return -ENOTTY;

	return func(vgpu, index, start, count, flags, data);
}

static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
			     unsigned long arg)
{
	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
	unsigned long minsz;

	gvt_dbg_core("vgpu%d ioctl, cmd: %d\n", vgpu->id, cmd);

	if (cmd == VFIO_DEVICE_GET_INFO) {
		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_PCI;
		info.flags |= VFIO_DEVICE_FLAGS_RESET;
		info.num_regions = VFIO_PCI_NUM_REGIONS;
		info.num_irqs = VFIO_PCI_NUM_IRQS;

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

	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
		struct vfio_region_info info;
		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
		int i, ret;
		struct vfio_region_info_cap_sparse_mmap *sparse = NULL;
		size_t size;
		int nr_areas = 1;
		int cap_type_id;

		minsz = offsetofend(struct vfio_region_info, offset);

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

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

		switch (info.index) {
		case VFIO_PCI_CONFIG_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = INTEL_GVT_MAX_CFG_SPACE_SZ;
			info.flags = VFIO_REGION_INFO_FLAG_READ |
				     VFIO_REGION_INFO_FLAG_WRITE;
			break;
		case VFIO_PCI_BAR0_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = vgpu->cfg_space.bar[info.index].size;
			if (!info.size) {
				info.flags = 0;
				break;
			}

			info.flags = VFIO_REGION_INFO_FLAG_READ |
				     VFIO_REGION_INFO_FLAG_WRITE;
			break;
		case VFIO_PCI_BAR1_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = 0;
			info.flags = 0;
			break;
		case VFIO_PCI_BAR2_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.flags = VFIO_REGION_INFO_FLAG_CAPS |
					VFIO_REGION_INFO_FLAG_MMAP |
					VFIO_REGION_INFO_FLAG_READ |
					VFIO_REGION_INFO_FLAG_WRITE;
			info.size = gvt_aperture_sz(vgpu->gvt);

			size = sizeof(*sparse) +
					(nr_areas * sizeof(*sparse->areas));
			sparse = kzalloc(size, GFP_KERNEL);
			if (!sparse)
				return -ENOMEM;

			sparse->nr_areas = nr_areas;
			cap_type_id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
			sparse->areas[0].offset =
					PAGE_ALIGN(vgpu_aperture_offset(vgpu));
			sparse->areas[0].size = vgpu_aperture_sz(vgpu);
			break;

		case VFIO_PCI_BAR3_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = 0;

			info.flags = 0;
			gvt_dbg_core("get region info bar:%d\n", info.index);
			break;

		case VFIO_PCI_ROM_REGION_INDEX:
		case VFIO_PCI_VGA_REGION_INDEX:
			gvt_dbg_core("get region info index:%d\n", info.index);
			break;
		default:
			{
				struct vfio_region_info_cap_type cap_type;

				if (info.index >= VFIO_PCI_NUM_REGIONS +
						vgpu->vdev.num_regions)
					return -EINVAL;

				i = info.index - VFIO_PCI_NUM_REGIONS;

				info.offset =
					VFIO_PCI_INDEX_TO_OFFSET(info.index);
				info.size = vgpu->vdev.region[i].size;
				info.flags = vgpu->vdev.region[i].flags;

				cap_type.type = vgpu->vdev.region[i].type;
				cap_type.subtype = vgpu->vdev.region[i].subtype;

				ret = vfio_info_add_capability(&caps,
						VFIO_REGION_INFO_CAP_TYPE,
						&cap_type);
				if (ret)
					return ret;
			}
		}

		if ((info.flags & VFIO_REGION_INFO_FLAG_CAPS) && sparse) {
			switch (cap_type_id) {
			case VFIO_REGION_INFO_CAP_SPARSE_MMAP:
				ret = vfio_info_add_capability(&caps,
					VFIO_REGION_INFO_CAP_SPARSE_MMAP,
					sparse);
				kfree(sparse);
				if (ret)
					return ret;
				break;
			default:
				return -EINVAL;
			}
		}

		if (caps.size) {
			if (info.argsz < sizeof(info) + caps.size) {
				info.argsz = sizeof(info) + caps.size;
				info.cap_offset = 0;
			} else {
				vfio_info_cap_shift(&caps, sizeof(info));
				if (copy_to_user((void __user *)arg +
						  sizeof(info), caps.buf,
						  caps.size)) {
					kfree(caps.buf);
					return -EFAULT;
				}
				info.cap_offset = sizeof(info);
			}

			kfree(caps.buf);
		}

		return copy_to_user((void __user *)arg, &info, minsz) ?
			-EFAULT : 0;
	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
		struct vfio_irq_info info;

		minsz = offsetofend(struct vfio_irq_info, count);

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

		if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS)
			return -EINVAL;

		switch (info.index) {
		case VFIO_PCI_INTX_IRQ_INDEX:
		case VFIO_PCI_MSI_IRQ_INDEX:
			break;
		default:
			return -EINVAL;
		}

		info.flags = VFIO_IRQ_INFO_EVENTFD;

		info.count = intel_vgpu_get_irq_count(vgpu, info.index);

		if (info.index == VFIO_PCI_INTX_IRQ_INDEX)
			info.flags |= (VFIO_IRQ_INFO_MASKABLE |
				       VFIO_IRQ_INFO_AUTOMASKED);
		else
			info.flags |= VFIO_IRQ_INFO_NORESIZE;

		return copy_to_user((void __user *)arg, &info, minsz) ?
			-EFAULT : 0;
	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
		struct vfio_irq_set hdr;
		u8 *data = NULL;
		int ret = 0;
		size_t data_size = 0;

		minsz = offsetofend(struct vfio_irq_set, count);

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

		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
			int max = intel_vgpu_get_irq_count(vgpu, hdr.index);

			ret = vfio_set_irqs_validate_and_prepare(&hdr, max,
						VFIO_PCI_NUM_IRQS, &data_size);
			if (ret) {
				gvt_vgpu_err("intel:vfio_set_irqs_validate_and_prepare failed\n");
				return -EINVAL;
			}
			if (data_size) {
				data = memdup_user((void __user *)(arg + minsz),
						   data_size);
				if (IS_ERR(data))
					return PTR_ERR(data);
			}
		}

		ret = intel_vgpu_set_irqs(vgpu, hdr.flags, hdr.index,
					hdr.start, hdr.count, data);
		kfree(data);

		return ret;
	} else if (cmd == VFIO_DEVICE_RESET) {
		intel_gvt_ops->vgpu_reset(vgpu);
		return 0;
	}

	return 0;
}

static ssize_t
vgpu_id_show(struct device *dev, struct device_attribute *attr,
	     char *buf)
{
	struct mdev_device *mdev = mdev_from_dev(dev);

	if (mdev) {
		struct intel_vgpu *vgpu = (struct intel_vgpu *)
			mdev_get_drvdata(mdev);
		return sprintf(buf, "%d\n", vgpu->id);
	}
	return sprintf(buf, "\n");
}

static ssize_t
hw_id_show(struct device *dev, struct device_attribute *attr,
	   char *buf)
{
	struct mdev_device *mdev = mdev_from_dev(dev);

	if (mdev) {
		struct intel_vgpu *vgpu = (struct intel_vgpu *)
			mdev_get_drvdata(mdev);
		return sprintf(buf, "%u\n",
			       vgpu->shadow_ctx->hw_id);
	}
	return sprintf(buf, "\n");
}

static DEVICE_ATTR_RO(vgpu_id);
static DEVICE_ATTR_RO(hw_id);

static struct attribute *intel_vgpu_attrs[] = {
	&dev_attr_vgpu_id.attr,
	&dev_attr_hw_id.attr,
	NULL
};

static const struct attribute_group intel_vgpu_group = {
	.name = "intel_vgpu",
	.attrs = intel_vgpu_attrs,
};

static const struct attribute_group *intel_vgpu_groups[] = {
	&intel_vgpu_group,
	NULL,
};

static const struct mdev_parent_ops intel_vgpu_ops = {
	.supported_type_groups	= intel_vgpu_type_groups,
	.mdev_attr_groups       = intel_vgpu_groups,
	.create			= intel_vgpu_create,
	.remove			= intel_vgpu_remove,

	.open			= intel_vgpu_open,
	.release		= intel_vgpu_release,

	.read			= intel_vgpu_read,
	.write			= intel_vgpu_write,
	.mmap			= intel_vgpu_mmap,
	.ioctl			= intel_vgpu_ioctl,
};

static int kvmgt_host_init(struct device *dev, void *gvt, const void *ops)
{
	if (!intel_gvt_init_vgpu_type_groups(gvt))
		return -EFAULT;

	intel_gvt_ops = ops;

	return mdev_register_device(dev, &intel_vgpu_ops);
}

static void kvmgt_host_exit(struct device *dev, void *gvt)
{
	intel_gvt_cleanup_vgpu_type_groups(gvt);
	mdev_unregister_device(dev);
}

static int kvmgt_write_protect_add(unsigned long handle, u64 gfn)
{
	struct kvmgt_guest_info *info;
	struct kvm *kvm;
	struct kvm_memory_slot *slot;
	int idx;

	if (!handle_valid(handle))
		return -ESRCH;

	info = (struct kvmgt_guest_info *)handle;
	kvm = info->kvm;

	idx = srcu_read_lock(&kvm->srcu);
	slot = gfn_to_memslot(kvm, gfn);
	if (!slot) {
		srcu_read_unlock(&kvm->srcu, idx);
		return -EINVAL;
	}

	spin_lock(&kvm->mmu_lock);

	if (kvmgt_gfn_is_write_protected(info, gfn))
		goto out;

	kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
	kvmgt_protect_table_add(info, gfn);

out:
	spin_unlock(&kvm->mmu_lock);
	srcu_read_unlock(&kvm->srcu, idx);
	return 0;
}

static int kvmgt_write_protect_remove(unsigned long handle, u64 gfn)
{
	struct kvmgt_guest_info *info;
	struct kvm *kvm;
	struct kvm_memory_slot *slot;
	int idx;

	if (!handle_valid(handle))
		return 0;

	info = (struct kvmgt_guest_info *)handle;
	kvm = info->kvm;

	idx = srcu_read_lock(&kvm->srcu);
	slot = gfn_to_memslot(kvm, gfn);
	if (!slot) {
		srcu_read_unlock(&kvm->srcu, idx);
		return -EINVAL;
	}

	spin_lock(&kvm->mmu_lock);

	if (!kvmgt_gfn_is_write_protected(info, gfn))
		goto out;

	kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
	kvmgt_protect_table_del(info, gfn);

out:
	spin_unlock(&kvm->mmu_lock);
	srcu_read_unlock(&kvm->srcu, idx);
	return 0;
}

static void kvmgt_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa,
		const u8 *val, int len,
		struct kvm_page_track_notifier_node *node)
{
	struct kvmgt_guest_info *info = container_of(node,
					struct kvmgt_guest_info, track_node);

	if (kvmgt_gfn_is_write_protected(info, gpa_to_gfn(gpa)))
		intel_gvt_ops->emulate_mmio_write(info->vgpu, gpa,
					(void *)val, len);
}

static void kvmgt_page_track_flush_slot(struct kvm *kvm,
		struct kvm_memory_slot *slot,
		struct kvm_page_track_notifier_node *node)
{
	int i;
	gfn_t gfn;
	struct kvmgt_guest_info *info = container_of(node,
					struct kvmgt_guest_info, track_node);

	spin_lock(&kvm->mmu_lock);
	for (i = 0; i < slot->npages; i++) {
		gfn = slot->base_gfn + i;
		if (kvmgt_gfn_is_write_protected(info, gfn)) {
			kvm_slot_page_track_remove_page(kvm, slot, gfn,
						KVM_PAGE_TRACK_WRITE);
			kvmgt_protect_table_del(info, gfn);
		}
	}
	spin_unlock(&kvm->mmu_lock);
}

static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu, struct kvm *kvm)
{
	struct intel_vgpu *itr;
	struct kvmgt_guest_info *info;
	int id;
	bool ret = false;

	mutex_lock(&vgpu->gvt->lock);
	for_each_active_vgpu(vgpu->gvt, itr, id) {
		if (!handle_valid(itr->handle))
			continue;

		info = (struct kvmgt_guest_info *)itr->handle;
		if (kvm && kvm == info->kvm) {
			ret = true;
			goto out;
		}
	}
out:
	mutex_unlock(&vgpu->gvt->lock);
	return ret;
}

static int kvmgt_guest_init(struct mdev_device *mdev)
{
	struct kvmgt_guest_info *info;
	struct intel_vgpu *vgpu;
	struct kvm *kvm;

	vgpu = mdev_get_drvdata(mdev);
	if (handle_valid(vgpu->handle))
		return -EEXIST;

	kvm = vgpu->vdev.kvm;
	if (!kvm || kvm->mm != current->mm) {
		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
		return -ESRCH;
	}

	if (__kvmgt_vgpu_exist(vgpu, kvm))
		return -EEXIST;

	info = vzalloc(sizeof(struct kvmgt_guest_info));
	if (!info)
		return -ENOMEM;

	vgpu->handle = (unsigned long)info;
	info->vgpu = vgpu;
	info->kvm = kvm;
	kvm_get_kvm(info->kvm);

	kvmgt_protect_table_init(info);
	gvt_cache_init(vgpu);

	info->track_node.track_write = kvmgt_page_track_write;
	info->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
	kvm_page_track_register_notifier(kvm, &info->track_node);

	return 0;
}

static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
{
	kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
	kvm_put_kvm(info->kvm);
	kvmgt_protect_table_destroy(info);
	gvt_cache_destroy(info->vgpu);
	vfree(info);

	return true;
}

static int kvmgt_attach_vgpu(void *vgpu, unsigned long *handle)
{
	/* nothing to do here */
	return 0;
}

static void kvmgt_detach_vgpu(unsigned long handle)
{
	/* nothing to do here */
}

static int kvmgt_inject_msi(unsigned long handle, u32 addr, u16 data)
{
	struct kvmgt_guest_info *info;
	struct intel_vgpu *vgpu;

	if (!handle_valid(handle))
		return -ESRCH;

	info = (struct kvmgt_guest_info *)handle;
	vgpu = info->vgpu;

	if (eventfd_signal(vgpu->vdev.msi_trigger, 1) == 1)
		return 0;

	return -EFAULT;
}

static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
{
	unsigned long iova, pfn;
	struct kvmgt_guest_info *info;
	struct device *dev;
	struct intel_vgpu *vgpu;
	int rc;

	if (!handle_valid(handle))
		return INTEL_GVT_INVALID_ADDR;

	info = (struct kvmgt_guest_info *)handle;
	vgpu = info->vgpu;
	iova = gvt_cache_find(info->vgpu, gfn);
	if (iova != INTEL_GVT_INVALID_ADDR)
		return iova;

	pfn = INTEL_GVT_INVALID_ADDR;
	dev = mdev_dev(info->vgpu->vdev.mdev);
	rc = vfio_pin_pages(dev, &gfn, 1, IOMMU_READ | IOMMU_WRITE, &pfn);
	if (rc != 1) {
		gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n",
			gfn, rc);
		return INTEL_GVT_INVALID_ADDR;
	}
	/* transfer to host iova for GFX to use DMA */
	rc = gvt_dma_map_iova(info->vgpu, pfn, &iova);
	if (rc) {
		gvt_vgpu_err("gvt_dma_map_iova failed for gfn: 0x%lx\n", gfn);
		vfio_unpin_pages(dev, &gfn, 1);
		return INTEL_GVT_INVALID_ADDR;
	}

	gvt_cache_add(info->vgpu, gfn, iova);
	return iova;
}

static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa,
			void *buf, unsigned long len, bool write)
{
	struct kvmgt_guest_info *info;
	struct kvm *kvm;
	int idx, ret;
	bool kthread = current->mm == NULL;

	if (!handle_valid(handle))
		return -ESRCH;

	info = (struct kvmgt_guest_info *)handle;
	kvm = info->kvm;

	if (kthread)
		use_mm(kvm->mm);

	idx = srcu_read_lock(&kvm->srcu);
	ret = write ? kvm_write_guest(kvm, gpa, buf, len) :
		      kvm_read_guest(kvm, gpa, buf, len);
	srcu_read_unlock(&kvm->srcu, idx);

	if (kthread)
		unuse_mm(kvm->mm);

	return ret;
}

static int kvmgt_read_gpa(unsigned long handle, unsigned long gpa,
			void *buf, unsigned long len)
{
	return kvmgt_rw_gpa(handle, gpa, buf, len, false);
}

static int kvmgt_write_gpa(unsigned long handle, unsigned long gpa,
			void *buf, unsigned long len)
{
	return kvmgt_rw_gpa(handle, gpa, buf, len, true);
}

static unsigned long kvmgt_virt_to_pfn(void *addr)
{
	return PFN_DOWN(__pa(addr));
}

struct intel_gvt_mpt kvmgt_mpt = {
	.host_init = kvmgt_host_init,
	.host_exit = kvmgt_host_exit,
	.attach_vgpu = kvmgt_attach_vgpu,
	.detach_vgpu = kvmgt_detach_vgpu,
	.inject_msi = kvmgt_inject_msi,
	.from_virt_to_mfn = kvmgt_virt_to_pfn,
	.set_wp_page = kvmgt_write_protect_add,
	.unset_wp_page = kvmgt_write_protect_remove,
	.read_gpa = kvmgt_read_gpa,
	.write_gpa = kvmgt_write_gpa,
	.gfn_to_mfn = kvmgt_gfn_to_pfn,
};
EXPORT_SYMBOL_GPL(kvmgt_mpt);

static int __init kvmgt_init(void)
{
	return 0;
}

static void __exit kvmgt_exit(void)
{
}

module_init(kvmgt_init);
module_exit(kvmgt_exit);

MODULE_LICENSE("GPL and additional rights");
MODULE_AUTHOR("Intel Corporation");