summaryrefslogtreecommitdiff
path: root/drivers/vdpa/vdpa.c
blob: f15fb11010a85016bb3054db7ad6fdd7da32a2a2 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * vDPA bus.
 *
 * Copyright (c) 2020, Red Hat. All rights reserved.
 *     Author: Jason Wang <jasowang@redhat.com>
 *
 */

#include <linux/module.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/vdpa.h>
#include <uapi/linux/vdpa.h>
#include <net/genetlink.h>
#include <linux/mod_devicetable.h>
#include <linux/virtio_ids.h>

static LIST_HEAD(mdev_head);
/* A global mutex that protects vdpa management device and device level operations. */
static DECLARE_RWSEM(vdpa_dev_lock);
static DEFINE_IDA(vdpa_index_ida);

void vdpa_set_status(struct vdpa_device *vdev, u8 status)
{
	down_write(&vdev->cf_lock);
	vdev->config->set_status(vdev, status);
	up_write(&vdev->cf_lock);
}
EXPORT_SYMBOL(vdpa_set_status);

static struct genl_family vdpa_nl_family;

static int vdpa_dev_probe(struct device *d)
{
	struct vdpa_device *vdev = dev_to_vdpa(d);
	struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver);
	const struct vdpa_config_ops *ops = vdev->config;
	u32 max_num, min_num = 1;
	int ret = 0;

	max_num = ops->get_vq_num_max(vdev);
	if (ops->get_vq_num_min)
		min_num = ops->get_vq_num_min(vdev);
	if (max_num < min_num)
		return -EINVAL;

	if (drv && drv->probe)
		ret = drv->probe(vdev);

	return ret;
}

static void vdpa_dev_remove(struct device *d)
{
	struct vdpa_device *vdev = dev_to_vdpa(d);
	struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver);

	if (drv && drv->remove)
		drv->remove(vdev);
}

static int vdpa_dev_match(struct device *dev, struct device_driver *drv)
{
	struct vdpa_device *vdev = dev_to_vdpa(dev);

	/* Check override first, and if set, only use the named driver */
	if (vdev->driver_override)
		return strcmp(vdev->driver_override, drv->name) == 0;

	/* Currently devices must be supported by all vDPA bus drivers */
	return 1;
}

static ssize_t driver_override_store(struct device *dev,
				     struct device_attribute *attr,
				     const char *buf, size_t count)
{
	struct vdpa_device *vdev = dev_to_vdpa(dev);
	const char *driver_override, *old;
	char *cp;

	/* We need to keep extra room for a newline */
	if (count >= (PAGE_SIZE - 1))
		return -EINVAL;

	driver_override = kstrndup(buf, count, GFP_KERNEL);
	if (!driver_override)
		return -ENOMEM;

	cp = strchr(driver_override, '\n');
	if (cp)
		*cp = '\0';

	device_lock(dev);
	old = vdev->driver_override;
	if (strlen(driver_override)) {
		vdev->driver_override = driver_override;
	} else {
		kfree(driver_override);
		vdev->driver_override = NULL;
	}
	device_unlock(dev);

	kfree(old);

	return count;
}

static ssize_t driver_override_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	struct vdpa_device *vdev = dev_to_vdpa(dev);
	ssize_t len;

	device_lock(dev);
	len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override);
	device_unlock(dev);

	return len;
}
static DEVICE_ATTR_RW(driver_override);

static struct attribute *vdpa_dev_attrs[] = {
	&dev_attr_driver_override.attr,
	NULL,
};

static const struct attribute_group vdpa_dev_group = {
	.attrs  = vdpa_dev_attrs,
};
__ATTRIBUTE_GROUPS(vdpa_dev);

static struct bus_type vdpa_bus = {
	.name  = "vdpa",
	.dev_groups = vdpa_dev_groups,
	.match = vdpa_dev_match,
	.probe = vdpa_dev_probe,
	.remove = vdpa_dev_remove,
};

static void vdpa_release_dev(struct device *d)
{
	struct vdpa_device *vdev = dev_to_vdpa(d);
	const struct vdpa_config_ops *ops = vdev->config;

	if (ops->free)
		ops->free(vdev);

	ida_simple_remove(&vdpa_index_ida, vdev->index);
	kfree(vdev->driver_override);
	kfree(vdev);
}

/**
 * __vdpa_alloc_device - allocate and initilaize a vDPA device
 * This allows driver to some prepartion after device is
 * initialized but before registered.
 * @parent: the parent device
 * @config: the bus operations that is supported by this device
 * @ngroups: number of groups supported by this device
 * @nas: number of address spaces supported by this device
 * @size: size of the parent structure that contains private data
 * @name: name of the vdpa device; optional.
 * @use_va: indicate whether virtual address must be used by this device
 *
 * Driver should use vdpa_alloc_device() wrapper macro instead of
 * using this directly.
 *
 * Return: Returns an error when parent/config/dma_dev is not set or fail to get
 *	   ida.
 */
struct vdpa_device *__vdpa_alloc_device(struct device *parent,
					const struct vdpa_config_ops *config,
					unsigned int ngroups, unsigned int nas,
					size_t size, const char *name,
					bool use_va)
{
	struct vdpa_device *vdev;
	int err = -EINVAL;

	if (!config)
		goto err;

	if (!!config->dma_map != !!config->dma_unmap)
		goto err;

	/* It should only work for the device that use on-chip IOMMU */
	if (use_va && !(config->dma_map || config->set_map))
		goto err;

	err = -ENOMEM;
	vdev = kzalloc(size, GFP_KERNEL);
	if (!vdev)
		goto err;

	err = ida_alloc(&vdpa_index_ida, GFP_KERNEL);
	if (err < 0)
		goto err_ida;

	vdev->dev.bus = &vdpa_bus;
	vdev->dev.parent = parent;
	vdev->dev.release = vdpa_release_dev;
	vdev->index = err;
	vdev->config = config;
	vdev->features_valid = false;
	vdev->use_va = use_va;
	vdev->ngroups = ngroups;
	vdev->nas = nas;

	if (name)
		err = dev_set_name(&vdev->dev, "%s", name);
	else
		err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
	if (err)
		goto err_name;

	init_rwsem(&vdev->cf_lock);
	device_initialize(&vdev->dev);

	return vdev;

err_name:
	ida_simple_remove(&vdpa_index_ida, vdev->index);
err_ida:
	kfree(vdev);
err:
	return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(__vdpa_alloc_device);

static int vdpa_name_match(struct device *dev, const void *data)
{
	struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev);

	return (strcmp(dev_name(&vdev->dev), data) == 0);
}

static int __vdpa_register_device(struct vdpa_device *vdev, u32 nvqs)
{
	struct device *dev;

	vdev->nvqs = nvqs;

	lockdep_assert_held(&vdpa_dev_lock);
	dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match);
	if (dev) {
		put_device(dev);
		return -EEXIST;
	}
	return device_add(&vdev->dev);
}

/**
 * _vdpa_register_device - register a vDPA device with vdpa lock held
 * Caller must have a succeed call of vdpa_alloc_device() before.
 * Caller must invoke this routine in the management device dev_add()
 * callback after setting up valid mgmtdev for this vdpa device.
 * @vdev: the vdpa device to be registered to vDPA bus
 * @nvqs: number of virtqueues supported by this device
 *
 * Return: Returns an error when fail to add device to vDPA bus
 */
int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs)
{
	if (!vdev->mdev)
		return -EINVAL;

	return __vdpa_register_device(vdev, nvqs);
}
EXPORT_SYMBOL_GPL(_vdpa_register_device);

/**
 * vdpa_register_device - register a vDPA device
 * Callers must have a succeed call of vdpa_alloc_device() before.
 * @vdev: the vdpa device to be registered to vDPA bus
 * @nvqs: number of virtqueues supported by this device
 *
 * Return: Returns an error when fail to add to vDPA bus
 */
int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs)
{
	int err;

	down_write(&vdpa_dev_lock);
	err = __vdpa_register_device(vdev, nvqs);
	up_write(&vdpa_dev_lock);
	return err;
}
EXPORT_SYMBOL_GPL(vdpa_register_device);

/**
 * _vdpa_unregister_device - unregister a vDPA device
 * Caller must invoke this routine as part of management device dev_del()
 * callback.
 * @vdev: the vdpa device to be unregisted from vDPA bus
 */
void _vdpa_unregister_device(struct vdpa_device *vdev)
{
	lockdep_assert_held(&vdpa_dev_lock);
	WARN_ON(!vdev->mdev);
	device_unregister(&vdev->dev);
}
EXPORT_SYMBOL_GPL(_vdpa_unregister_device);

/**
 * vdpa_unregister_device - unregister a vDPA device
 * @vdev: the vdpa device to be unregisted from vDPA bus
 */
void vdpa_unregister_device(struct vdpa_device *vdev)
{
	down_write(&vdpa_dev_lock);
	device_unregister(&vdev->dev);
	up_write(&vdpa_dev_lock);
}
EXPORT_SYMBOL_GPL(vdpa_unregister_device);

/**
 * __vdpa_register_driver - register a vDPA device driver
 * @drv: the vdpa device driver to be registered
 * @owner: module owner of the driver
 *
 * Return: Returns an err when fail to do the registration
 */
int __vdpa_register_driver(struct vdpa_driver *drv, struct module *owner)
{
	drv->driver.bus = &vdpa_bus;
	drv->driver.owner = owner;

	return driver_register(&drv->driver);
}
EXPORT_SYMBOL_GPL(__vdpa_register_driver);

/**
 * vdpa_unregister_driver - unregister a vDPA device driver
 * @drv: the vdpa device driver to be unregistered
 */
void vdpa_unregister_driver(struct vdpa_driver *drv)
{
	driver_unregister(&drv->driver);
}
EXPORT_SYMBOL_GPL(vdpa_unregister_driver);

/**
 * vdpa_mgmtdev_register - register a vdpa management device
 *
 * @mdev: Pointer to vdpa management device
 * vdpa_mgmtdev_register() register a vdpa management device which supports
 * vdpa device management.
 * Return: Returns 0 on success or failure when required callback ops are not
 *         initialized.
 */
int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev)
{
	if (!mdev->device || !mdev->ops || !mdev->ops->dev_add || !mdev->ops->dev_del)
		return -EINVAL;

	INIT_LIST_HEAD(&mdev->list);
	down_write(&vdpa_dev_lock);
	list_add_tail(&mdev->list, &mdev_head);
	up_write(&vdpa_dev_lock);
	return 0;
}
EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register);

static int vdpa_match_remove(struct device *dev, void *data)
{
	struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev);
	struct vdpa_mgmt_dev *mdev = vdev->mdev;

	if (mdev == data)
		mdev->ops->dev_del(mdev, vdev);
	return 0;
}

void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev)
{
	down_write(&vdpa_dev_lock);

	list_del(&mdev->list);

	/* Filter out all the entries belong to this management device and delete it. */
	bus_for_each_dev(&vdpa_bus, NULL, mdev, vdpa_match_remove);

	up_write(&vdpa_dev_lock);
}
EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister);

static void vdpa_get_config_unlocked(struct vdpa_device *vdev,
				     unsigned int offset,
				     void *buf, unsigned int len)
{
	const struct vdpa_config_ops *ops = vdev->config;

	/*
	 * Config accesses aren't supposed to trigger before features are set.
	 * If it does happen we assume a legacy guest.
	 */
	if (!vdev->features_valid)
		vdpa_set_features_unlocked(vdev, 0);
	ops->get_config(vdev, offset, buf, len);
}

/**
 * vdpa_get_config - Get one or more device configuration fields.
 * @vdev: vdpa device to operate on
 * @offset: starting byte offset of the field
 * @buf: buffer pointer to read to
 * @len: length of the configuration fields in bytes
 */
void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
		     void *buf, unsigned int len)
{
	down_read(&vdev->cf_lock);
	vdpa_get_config_unlocked(vdev, offset, buf, len);
	up_read(&vdev->cf_lock);
}
EXPORT_SYMBOL_GPL(vdpa_get_config);

/**
 * vdpa_set_config - Set one or more device configuration fields.
 * @vdev: vdpa device to operate on
 * @offset: starting byte offset of the field
 * @buf: buffer pointer to read from
 * @length: length of the configuration fields in bytes
 */
void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset,
		     const void *buf, unsigned int length)
{
	down_write(&vdev->cf_lock);
	vdev->config->set_config(vdev, offset, buf, length);
	up_write(&vdev->cf_lock);
}
EXPORT_SYMBOL_GPL(vdpa_set_config);

static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev,
				 const char *busname, const char *devname)
{
	/* Bus name is optional for simulated management device, so ignore the
	 * device with bus if bus attribute is provided.
	 */
	if ((busname && !mdev->device->bus) || (!busname && mdev->device->bus))
		return false;

	if (!busname && strcmp(dev_name(mdev->device), devname) == 0)
		return true;

	if (busname && (strcmp(mdev->device->bus->name, busname) == 0) &&
	    (strcmp(dev_name(mdev->device), devname) == 0))
		return true;

	return false;
}

static struct vdpa_mgmt_dev *vdpa_mgmtdev_get_from_attr(struct nlattr **attrs)
{
	struct vdpa_mgmt_dev *mdev;
	const char *busname = NULL;
	const char *devname;

	if (!attrs[VDPA_ATTR_MGMTDEV_DEV_NAME])
		return ERR_PTR(-EINVAL);
	devname = nla_data(attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]);
	if (attrs[VDPA_ATTR_MGMTDEV_BUS_NAME])
		busname = nla_data(attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]);

	list_for_each_entry(mdev, &mdev_head, list) {
		if (mgmtdev_handle_match(mdev, busname, devname))
			return mdev;
	}
	return ERR_PTR(-ENODEV);
}

static int vdpa_nl_mgmtdev_handle_fill(struct sk_buff *msg, const struct vdpa_mgmt_dev *mdev)
{
	if (mdev->device->bus &&
	    nla_put_string(msg, VDPA_ATTR_MGMTDEV_BUS_NAME, mdev->device->bus->name))
		return -EMSGSIZE;
	if (nla_put_string(msg, VDPA_ATTR_MGMTDEV_DEV_NAME, dev_name(mdev->device)))
		return -EMSGSIZE;
	return 0;
}

static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *msg,
			     u32 portid, u32 seq, int flags)
{
	u64 supported_classes = 0;
	void *hdr;
	int i = 0;
	int err;

	hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_MGMTDEV_NEW);
	if (!hdr)
		return -EMSGSIZE;
	err = vdpa_nl_mgmtdev_handle_fill(msg, mdev);
	if (err)
		goto msg_err;

	while (mdev->id_table[i].device) {
		if (mdev->id_table[i].device <= 63)
			supported_classes |= BIT_ULL(mdev->id_table[i].device);
		i++;
	}

	if (nla_put_u64_64bit(msg, VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES,
			      supported_classes, VDPA_ATTR_UNSPEC)) {
		err = -EMSGSIZE;
		goto msg_err;
	}
	if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,
			mdev->max_supported_vqs)) {
		err = -EMSGSIZE;
		goto msg_err;
	}
	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES,
			      mdev->supported_features, VDPA_ATTR_PAD)) {
		err = -EMSGSIZE;
		goto msg_err;
	}

	genlmsg_end(msg, hdr);
	return 0;

msg_err:
	genlmsg_cancel(msg, hdr);
	return err;
}

static int vdpa_nl_cmd_mgmtdev_get_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct vdpa_mgmt_dev *mdev;
	struct sk_buff *msg;
	int err;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	down_read(&vdpa_dev_lock);
	mdev = vdpa_mgmtdev_get_from_attr(info->attrs);
	if (IS_ERR(mdev)) {
		up_read(&vdpa_dev_lock);
		NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified mgmt device");
		err = PTR_ERR(mdev);
		goto out;
	}

	err = vdpa_mgmtdev_fill(mdev, msg, info->snd_portid, info->snd_seq, 0);
	up_read(&vdpa_dev_lock);
	if (err)
		goto out;
	err = genlmsg_reply(msg, info);
	return err;

out:
	nlmsg_free(msg);
	return err;
}

static int
vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
{
	struct vdpa_mgmt_dev *mdev;
	int start = cb->args[0];
	int idx = 0;
	int err;

	down_read(&vdpa_dev_lock);
	list_for_each_entry(mdev, &mdev_head, list) {
		if (idx < start) {
			idx++;
			continue;
		}
		err = vdpa_mgmtdev_fill(mdev, msg, NETLINK_CB(cb->skb).portid,
					cb->nlh->nlmsg_seq, NLM_F_MULTI);
		if (err)
			goto out;
		idx++;
	}
out:
	up_read(&vdpa_dev_lock);
	cb->args[0] = idx;
	return msg->len;
}

#define VDPA_DEV_NET_ATTRS_MASK (BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | \
				 BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU)     | \
				 BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP))

static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct vdpa_dev_set_config config = {};
	struct nlattr **nl_attrs = info->attrs;
	struct vdpa_mgmt_dev *mdev;
	const u8 *macaddr;
	const char *name;
	int err = 0;

	if (!info->attrs[VDPA_ATTR_DEV_NAME])
		return -EINVAL;

	name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);

	if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) {
		macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]);
		memcpy(config.net.mac, macaddr, sizeof(config.net.mac));
		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR);
	}
	if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) {
		config.net.mtu =
			nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]);
		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU);
	}
	if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]) {
		config.net.max_vq_pairs =
			nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]);
		if (!config.net.max_vq_pairs) {
			NL_SET_ERR_MSG_MOD(info->extack,
					   "At least one pair of VQs is required");
			return -EINVAL;
		}
		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
	}

	/* Skip checking capability if user didn't prefer to configure any
	 * device networking attributes. It is likely that user might have used
	 * a device specific method to configure such attributes or using device
	 * default attributes.
	 */
	if ((config.mask & VDPA_DEV_NET_ATTRS_MASK) &&
	    !netlink_capable(skb, CAP_NET_ADMIN))
		return -EPERM;

	down_write(&vdpa_dev_lock);
	mdev = vdpa_mgmtdev_get_from_attr(info->attrs);
	if (IS_ERR(mdev)) {
		NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified management device");
		err = PTR_ERR(mdev);
		goto err;
	}
	if ((config.mask & mdev->config_attr_mask) != config.mask) {
		NL_SET_ERR_MSG_MOD(info->extack,
				   "All provided attributes are not supported");
		err = -EOPNOTSUPP;
		goto err;
	}

	err = mdev->ops->dev_add(mdev, name, &config);
err:
	up_write(&vdpa_dev_lock);
	return err;
}

static int vdpa_nl_cmd_dev_del_set_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct vdpa_mgmt_dev *mdev;
	struct vdpa_device *vdev;
	struct device *dev;
	const char *name;
	int err = 0;

	if (!info->attrs[VDPA_ATTR_DEV_NAME])
		return -EINVAL;
	name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);

	down_write(&vdpa_dev_lock);
	dev = bus_find_device(&vdpa_bus, NULL, name, vdpa_name_match);
	if (!dev) {
		NL_SET_ERR_MSG_MOD(info->extack, "device not found");
		err = -ENODEV;
		goto dev_err;
	}
	vdev = container_of(dev, struct vdpa_device, dev);
	if (!vdev->mdev) {
		NL_SET_ERR_MSG_MOD(info->extack, "Only user created device can be deleted by user");
		err = -EINVAL;
		goto mdev_err;
	}
	mdev = vdev->mdev;
	mdev->ops->dev_del(mdev, vdev);
mdev_err:
	put_device(dev);
dev_err:
	up_write(&vdpa_dev_lock);
	return err;
}

static int
vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq,
	      int flags, struct netlink_ext_ack *extack)
{
	u16 max_vq_size;
	u16 min_vq_size = 1;
	u32 device_id;
	u32 vendor_id;
	void *hdr;
	int err;

	hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_DEV_NEW);
	if (!hdr)
		return -EMSGSIZE;

	err = vdpa_nl_mgmtdev_handle_fill(msg, vdev->mdev);
	if (err)
		goto msg_err;

	device_id = vdev->config->get_device_id(vdev);
	vendor_id = vdev->config->get_vendor_id(vdev);
	max_vq_size = vdev->config->get_vq_num_max(vdev);
	if (vdev->config->get_vq_num_min)
		min_vq_size = vdev->config->get_vq_num_min(vdev);

	err = -EMSGSIZE;
	if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev)))
		goto msg_err;
	if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id))
		goto msg_err;
	if (nla_put_u32(msg, VDPA_ATTR_DEV_VENDOR_ID, vendor_id))
		goto msg_err;
	if (nla_put_u32(msg, VDPA_ATTR_DEV_MAX_VQS, vdev->nvqs))
		goto msg_err;
	if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size))
		goto msg_err;
	if (nla_put_u16(msg, VDPA_ATTR_DEV_MIN_VQ_SIZE, min_vq_size))
		goto msg_err;

	genlmsg_end(msg, hdr);
	return 0;

msg_err:
	genlmsg_cancel(msg, hdr);
	return err;
}

static int vdpa_nl_cmd_dev_get_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct vdpa_device *vdev;
	struct sk_buff *msg;
	const char *devname;
	struct device *dev;
	int err;

	if (!info->attrs[VDPA_ATTR_DEV_NAME])
		return -EINVAL;
	devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);
	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	down_read(&vdpa_dev_lock);
	dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match);
	if (!dev) {
		NL_SET_ERR_MSG_MOD(info->extack, "device not found");
		err = -ENODEV;
		goto err;
	}
	vdev = container_of(dev, struct vdpa_device, dev);
	if (!vdev->mdev) {
		err = -EINVAL;
		goto mdev_err;
	}
	err = vdpa_dev_fill(vdev, msg, info->snd_portid, info->snd_seq, 0, info->extack);
	if (err)
		goto mdev_err;

	err = genlmsg_reply(msg, info);
	put_device(dev);
	up_read(&vdpa_dev_lock);
	return err;

mdev_err:
	put_device(dev);
err:
	up_read(&vdpa_dev_lock);
	nlmsg_free(msg);
	return err;
}

struct vdpa_dev_dump_info {
	struct sk_buff *msg;
	struct netlink_callback *cb;
	int start_idx;
	int idx;
};

static int vdpa_dev_dump(struct device *dev, void *data)
{
	struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev);
	struct vdpa_dev_dump_info *info = data;
	int err;

	if (!vdev->mdev)
		return 0;
	if (info->idx < info->start_idx) {
		info->idx++;
		return 0;
	}
	err = vdpa_dev_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid,
			    info->cb->nlh->nlmsg_seq, NLM_F_MULTI, info->cb->extack);
	if (err)
		return err;

	info->idx++;
	return 0;
}

static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
{
	struct vdpa_dev_dump_info info;

	info.msg = msg;
	info.cb = cb;
	info.start_idx = cb->args[0];
	info.idx = 0;

	down_read(&vdpa_dev_lock);
	bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_dump);
	up_read(&vdpa_dev_lock);
	cb->args[0] = info.idx;
	return msg->len;
}

static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev,
				       struct sk_buff *msg, u64 features,
				       const struct virtio_net_config *config)
{
	u16 val_u16;

	if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0)
		return 0;

	val_u16 = le16_to_cpu(config->max_virtqueue_pairs);
	return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16);
}

static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg)
{
	struct virtio_net_config config = {};
	u64 features;
	u16 val_u16;

	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));

	if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
		    config.mac))
		return -EMSGSIZE;

	val_u16 = le16_to_cpu(config.status);
	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16))
		return -EMSGSIZE;

	val_u16 = le16_to_cpu(config.mtu);
	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
		return -EMSGSIZE;

	features = vdev->config->get_driver_features(vdev);
	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features,
			      VDPA_ATTR_PAD))
		return -EMSGSIZE;

	return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config);
}

static int
vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq,
		     int flags, struct netlink_ext_ack *extack)
{
	u32 device_id;
	void *hdr;
	u8 status;
	int err;

	down_read(&vdev->cf_lock);
	status = vdev->config->get_status(vdev);
	if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
		NL_SET_ERR_MSG_MOD(extack, "Features negotiation not completed");
		err = -EAGAIN;
		goto out;
	}

	hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags,
			  VDPA_CMD_DEV_CONFIG_GET);
	if (!hdr) {
		err = -EMSGSIZE;
		goto out;
	}

	if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) {
		err = -EMSGSIZE;
		goto msg_err;
	}

	device_id = vdev->config->get_device_id(vdev);
	if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) {
		err = -EMSGSIZE;
		goto msg_err;
	}

	switch (device_id) {
	case VIRTIO_ID_NET:
		err = vdpa_dev_net_config_fill(vdev, msg);
		break;
	default:
		err = -EOPNOTSUPP;
		break;
	}
	if (err)
		goto msg_err;

	up_read(&vdev->cf_lock);
	genlmsg_end(msg, hdr);
	return 0;

msg_err:
	genlmsg_cancel(msg, hdr);
out:
	up_read(&vdev->cf_lock);
	return err;
}

static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg,
			       struct genl_info *info, u32 index)
{
	struct virtio_net_config config = {};
	u64 features;
	u16 max_vqp;
	u8 status;
	int err;

	status = vdev->config->get_status(vdev);
	if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
		NL_SET_ERR_MSG_MOD(info->extack, "feature negotiation not complete");
		return -EAGAIN;
	}
	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));

	max_vqp = le16_to_cpu(config.max_virtqueue_pairs);
	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
		return -EMSGSIZE;

	features = vdev->config->get_driver_features(vdev);
	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
			      features, VDPA_ATTR_PAD))
		return -EMSGSIZE;

	if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
		return -EMSGSIZE;

	err = vdev->config->get_vendor_vq_stats(vdev, index, msg, info->extack);
	if (err)
		return err;

	return 0;
}

static int vendor_stats_fill(struct vdpa_device *vdev, struct sk_buff *msg,
			     struct genl_info *info, u32 index)
{
	int err;

	down_read(&vdev->cf_lock);
	if (!vdev->config->get_vendor_vq_stats) {
		err = -EOPNOTSUPP;
		goto out;
	}

	err = vdpa_fill_stats_rec(vdev, msg, info, index);
out:
	up_read(&vdev->cf_lock);
	return err;
}

static int vdpa_dev_vendor_stats_fill(struct vdpa_device *vdev,
				      struct sk_buff *msg,
				      struct genl_info *info, u32 index)
{
	u32 device_id;
	void *hdr;
	int err;
	u32 portid = info->snd_portid;
	u32 seq = info->snd_seq;
	u32 flags = 0;

	hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags,
			  VDPA_CMD_DEV_VSTATS_GET);
	if (!hdr)
		return -EMSGSIZE;

	if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) {
		err = -EMSGSIZE;
		goto undo_msg;
	}

	device_id = vdev->config->get_device_id(vdev);
	if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) {
		err = -EMSGSIZE;
		goto undo_msg;
	}

	switch (device_id) {
	case VIRTIO_ID_NET:
		if (index > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX) {
			NL_SET_ERR_MSG_MOD(info->extack, "queue index excceeds max value");
			err = -ERANGE;
			break;
		}

		err = vendor_stats_fill(vdev, msg, info, index);
		break;
	default:
		err = -EOPNOTSUPP;
		break;
	}
	genlmsg_end(msg, hdr);

	return err;

undo_msg:
	genlmsg_cancel(msg, hdr);
	return err;
}

static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct vdpa_device *vdev;
	struct sk_buff *msg;
	const char *devname;
	struct device *dev;
	int err;

	if (!info->attrs[VDPA_ATTR_DEV_NAME])
		return -EINVAL;
	devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);
	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	down_read(&vdpa_dev_lock);
	dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match);
	if (!dev) {
		NL_SET_ERR_MSG_MOD(info->extack, "device not found");
		err = -ENODEV;
		goto dev_err;
	}
	vdev = container_of(dev, struct vdpa_device, dev);
	if (!vdev->mdev) {
		NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device");
		err = -EINVAL;
		goto mdev_err;
	}
	err = vdpa_dev_config_fill(vdev, msg, info->snd_portid, info->snd_seq,
				   0, info->extack);
	if (!err)
		err = genlmsg_reply(msg, info);

mdev_err:
	put_device(dev);
dev_err:
	up_read(&vdpa_dev_lock);
	if (err)
		nlmsg_free(msg);
	return err;
}

static int vdpa_dev_config_dump(struct device *dev, void *data)
{
	struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev);
	struct vdpa_dev_dump_info *info = data;
	int err;

	if (!vdev->mdev)
		return 0;
	if (info->idx < info->start_idx) {
		info->idx++;
		return 0;
	}
	err = vdpa_dev_config_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid,
				   info->cb->nlh->nlmsg_seq, NLM_F_MULTI,
				   info->cb->extack);
	if (err)
		return err;

	info->idx++;
	return 0;
}

static int
vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
{
	struct vdpa_dev_dump_info info;

	info.msg = msg;
	info.cb = cb;
	info.start_idx = cb->args[0];
	info.idx = 0;

	down_read(&vdpa_dev_lock);
	bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_config_dump);
	up_read(&vdpa_dev_lock);
	cb->args[0] = info.idx;
	return msg->len;
}

static int vdpa_nl_cmd_dev_stats_get_doit(struct sk_buff *skb,
					  struct genl_info *info)
{
	struct vdpa_device *vdev;
	struct sk_buff *msg;
	const char *devname;
	struct device *dev;
	u32 index;
	int err;

	if (!info->attrs[VDPA_ATTR_DEV_NAME])
		return -EINVAL;

	if (!info->attrs[VDPA_ATTR_DEV_QUEUE_INDEX])
		return -EINVAL;

	devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);
	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	index = nla_get_u32(info->attrs[VDPA_ATTR_DEV_QUEUE_INDEX]);
	down_read(&vdpa_dev_lock);
	dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match);
	if (!dev) {
		NL_SET_ERR_MSG_MOD(info->extack, "device not found");
		err = -ENODEV;
		goto dev_err;
	}
	vdev = container_of(dev, struct vdpa_device, dev);
	if (!vdev->mdev) {
		NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device");
		err = -EINVAL;
		goto mdev_err;
	}
	err = vdpa_dev_vendor_stats_fill(vdev, msg, info, index);
	if (err)
		goto mdev_err;

	err = genlmsg_reply(msg, info);

	put_device(dev);
	up_read(&vdpa_dev_lock);

	return err;

mdev_err:
	put_device(dev);
dev_err:
	nlmsg_free(msg);
	up_read(&vdpa_dev_lock);
	return err;
}

static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = {
	[VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING },
	[VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING },
	[VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING },
	[VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR,
	/* virtio spec 1.1 section 5.1.4.1 for valid MTU range */
	[VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68),
};

static const struct genl_ops vdpa_nl_ops[] = {
	{
		.cmd = VDPA_CMD_MGMTDEV_GET,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.doit = vdpa_nl_cmd_mgmtdev_get_doit,
		.dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit,
	},
	{
		.cmd = VDPA_CMD_DEV_NEW,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.doit = vdpa_nl_cmd_dev_add_set_doit,
		.flags = GENL_ADMIN_PERM,
	},
	{
		.cmd = VDPA_CMD_DEV_DEL,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.doit = vdpa_nl_cmd_dev_del_set_doit,
		.flags = GENL_ADMIN_PERM,
	},
	{
		.cmd = VDPA_CMD_DEV_GET,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.doit = vdpa_nl_cmd_dev_get_doit,
		.dumpit = vdpa_nl_cmd_dev_get_dumpit,
	},
	{
		.cmd = VDPA_CMD_DEV_CONFIG_GET,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.doit = vdpa_nl_cmd_dev_config_get_doit,
		.dumpit = vdpa_nl_cmd_dev_config_get_dumpit,
	},
	{
		.cmd = VDPA_CMD_DEV_VSTATS_GET,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.doit = vdpa_nl_cmd_dev_stats_get_doit,
		.flags = GENL_ADMIN_PERM,
	},
};

static struct genl_family vdpa_nl_family __ro_after_init = {
	.name = VDPA_GENL_NAME,
	.version = VDPA_GENL_VERSION,
	.maxattr = VDPA_ATTR_MAX,
	.policy = vdpa_nl_policy,
	.netnsok = false,
	.module = THIS_MODULE,
	.ops = vdpa_nl_ops,
	.n_ops = ARRAY_SIZE(vdpa_nl_ops),
};

static int vdpa_init(void)
{
	int err;

	err = bus_register(&vdpa_bus);
	if (err)
		return err;
	err = genl_register_family(&vdpa_nl_family);
	if (err)
		goto err;
	return 0;

err:
	bus_unregister(&vdpa_bus);
	return err;
}

static void __exit vdpa_exit(void)
{
	genl_unregister_family(&vdpa_nl_family);
	bus_unregister(&vdpa_bus);
	ida_destroy(&vdpa_index_ida);
}
core_initcall(vdpa_init);
module_exit(vdpa_exit);

MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
MODULE_LICENSE("GPL v2");