summaryrefslogtreecommitdiff
path: root/fs/fuse/virtio_fs.c
blob: dd52601416150339b5f234f720d6da1316cb4a7d (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
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
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
// SPDX-License-Identifier: GPL-2.0
/*
 * virtio-fs: Virtio Filesystem
 * Copyright (C) 2018 Red Hat, Inc.
 */

#include <linux/fs.h>
#include <linux/dax.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/group_cpus.h>
#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_fs.h>
#include <linux/delay.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/highmem.h>
#include <linux/cleanup.h>
#include <linux/uio.h>
#include "fuse_i.h"

/* Used to help calculate the FUSE connection's max_pages limit for a request's
 * size. Parts of the struct fuse_req are sliced into scattergather lists in
 * addition to the pages used, so this can help account for that overhead.
 */
#define FUSE_HEADER_OVERHEAD    4

/* List of virtio-fs device instances and a lock for the list. Also provides
 * mutual exclusion in device removal and mounting path
 */
static DEFINE_MUTEX(virtio_fs_mutex);
static LIST_HEAD(virtio_fs_instances);

/* The /sys/fs/virtio_fs/ kset */
static struct kset *virtio_fs_kset;

enum {
	VQ_HIPRIO,
	VQ_REQUEST
};

#define VQ_NAME_LEN	24

/* Per-virtqueue state */
struct virtio_fs_vq {
	spinlock_t lock;
	struct virtqueue *vq;     /* protected by ->lock */
	struct work_struct done_work;
	struct list_head queued_reqs;
	struct list_head end_reqs;	/* End these requests */
	struct work_struct dispatch_work;
	struct fuse_dev *fud;
	bool connected;
	long in_flight;
	struct completion in_flight_zero; /* No inflight requests */
	char name[VQ_NAME_LEN];
} ____cacheline_aligned_in_smp;

/* A virtio-fs device instance */
struct virtio_fs {
	struct kobject kobj;
	struct list_head list;    /* on virtio_fs_instances */
	char *tag;
	struct virtio_fs_vq *vqs;
	unsigned int nvqs;               /* number of virtqueues */
	unsigned int num_request_queues; /* number of request queues */
	struct dax_device *dax_dev;

	unsigned int *mq_map; /* index = cpu id, value = request vq id */

	/* DAX memory window where file contents are mapped */
	void *window_kaddr;
	phys_addr_t window_phys_addr;
	size_t window_len;
};

struct virtio_fs_forget_req {
	struct fuse_in_header ih;
	struct fuse_forget_in arg;
};

struct virtio_fs_forget {
	/* This request can be temporarily queued on virt queue */
	struct list_head list;
	struct virtio_fs_forget_req req;
};

struct virtio_fs_req_work {
	struct fuse_req *req;
	struct virtio_fs_vq *fsvq;
	struct work_struct done_work;
};

static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
				 struct fuse_req *req, bool in_flight);

static const struct constant_table dax_param_enums[] = {
	{"always",	FUSE_DAX_ALWAYS },
	{"never",	FUSE_DAX_NEVER },
	{"inode",	FUSE_DAX_INODE_USER },
	{}
};

enum {
	OPT_DAX,
	OPT_DAX_ENUM,
};

static const struct fs_parameter_spec virtio_fs_parameters[] = {
	fsparam_flag("dax", OPT_DAX),
	fsparam_enum("dax", OPT_DAX_ENUM, dax_param_enums),
	{}
};

static int virtio_fs_parse_param(struct fs_context *fsc,
				 struct fs_parameter *param)
{
	struct fs_parse_result result;
	struct fuse_fs_context *ctx = fsc->fs_private;
	int opt;

	opt = fs_parse(fsc, virtio_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case OPT_DAX:
		ctx->dax_mode = FUSE_DAX_ALWAYS;
		break;
	case OPT_DAX_ENUM:
		ctx->dax_mode = result.uint_32;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static void virtio_fs_free_fsc(struct fs_context *fsc)
{
	struct fuse_fs_context *ctx = fsc->fs_private;

	kfree(ctx);
}

static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
{
	struct virtio_fs *fs = vq->vdev->priv;

	return &fs->vqs[vq->index];
}

/* Should be called with fsvq->lock held. */
static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
{
	fsvq->in_flight++;
}

/* Should be called with fsvq->lock held. */
static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
{
	WARN_ON(fsvq->in_flight <= 0);
	fsvq->in_flight--;
	if (!fsvq->in_flight)
		complete(&fsvq->in_flight_zero);
}

static ssize_t tag_show(struct kobject *kobj,
		struct kobj_attribute *attr, char *buf)
{
	struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj);

	return sysfs_emit(buf, "%s\n", fs->tag);
}

static struct kobj_attribute virtio_fs_tag_attr = __ATTR_RO(tag);

static struct attribute *virtio_fs_attrs[] = {
	&virtio_fs_tag_attr.attr,
	NULL
};
ATTRIBUTE_GROUPS(virtio_fs);

static void virtio_fs_ktype_release(struct kobject *kobj)
{
	struct virtio_fs *vfs = container_of(kobj, struct virtio_fs, kobj);

	kfree(vfs->mq_map);
	kfree(vfs->vqs);
	kfree(vfs);
}

static const struct kobj_type virtio_fs_ktype = {
	.release = virtio_fs_ktype_release,
	.sysfs_ops = &kobj_sysfs_ops,
	.default_groups = virtio_fs_groups,
};

/* Make sure virtiofs_mutex is held */
static void virtio_fs_put(struct virtio_fs *fs)
{
	kobject_put(&fs->kobj);
}

static void virtio_fs_fiq_release(struct fuse_iqueue *fiq)
{
	struct virtio_fs *vfs = fiq->priv;

	mutex_lock(&virtio_fs_mutex);
	virtio_fs_put(vfs);
	mutex_unlock(&virtio_fs_mutex);
}

static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
{
	WARN_ON(fsvq->in_flight < 0);

	/* Wait for in flight requests to finish.*/
	spin_lock(&fsvq->lock);
	if (fsvq->in_flight) {
		/* We are holding virtio_fs_mutex. There should not be any
		 * waiters waiting for completion.
		 */
		reinit_completion(&fsvq->in_flight_zero);
		spin_unlock(&fsvq->lock);
		wait_for_completion(&fsvq->in_flight_zero);
	} else {
		spin_unlock(&fsvq->lock);
	}

	flush_work(&fsvq->done_work);
	flush_work(&fsvq->dispatch_work);
}

static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs)
{
	struct virtio_fs_vq *fsvq;
	int i;

	for (i = 0; i < fs->nvqs; i++) {
		fsvq = &fs->vqs[i];
		virtio_fs_drain_queue(fsvq);
	}
}

static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
{
	/* Provides mutual exclusion between ->remove and ->kill_sb
	 * paths. We don't want both of these draining queue at the
	 * same time. Current completion logic reinits completion
	 * and that means there should not be any other thread
	 * doing reinit or waiting for completion already.
	 */
	mutex_lock(&virtio_fs_mutex);
	virtio_fs_drain_all_queues_locked(fs);
	mutex_unlock(&virtio_fs_mutex);
}

static void virtio_fs_start_all_queues(struct virtio_fs *fs)
{
	struct virtio_fs_vq *fsvq;
	int i;

	for (i = 0; i < fs->nvqs; i++) {
		fsvq = &fs->vqs[i];
		spin_lock(&fsvq->lock);
		fsvq->connected = true;
		spin_unlock(&fsvq->lock);
	}
}

/* Add a new instance to the list or return -EEXIST if tag name exists*/
static int virtio_fs_add_instance(struct virtio_device *vdev,
				  struct virtio_fs *fs)
{
	struct virtio_fs *fs2;
	int ret;

	mutex_lock(&virtio_fs_mutex);

	list_for_each_entry(fs2, &virtio_fs_instances, list) {
		if (strcmp(fs->tag, fs2->tag) == 0) {
			mutex_unlock(&virtio_fs_mutex);
			return -EEXIST;
		}
	}

	/* Use the virtio_device's index as a unique identifier, there is no
	 * need to allocate our own identifiers because the virtio_fs instance
	 * is only visible to userspace as long as the underlying virtio_device
	 * exists.
	 */
	fs->kobj.kset = virtio_fs_kset;
	ret = kobject_add(&fs->kobj, NULL, "%d", vdev->index);
	if (ret < 0) {
		mutex_unlock(&virtio_fs_mutex);
		return ret;
	}

	ret = sysfs_create_link(&fs->kobj, &vdev->dev.kobj, "device");
	if (ret < 0) {
		kobject_del(&fs->kobj);
		mutex_unlock(&virtio_fs_mutex);
		return ret;
	}

	list_add_tail(&fs->list, &virtio_fs_instances);

	mutex_unlock(&virtio_fs_mutex);

	kobject_uevent(&fs->kobj, KOBJ_ADD);

	return 0;
}

/* Return the virtio_fs with a given tag, or NULL */
static struct virtio_fs *virtio_fs_find_instance(const char *tag)
{
	struct virtio_fs *fs;

	mutex_lock(&virtio_fs_mutex);

	list_for_each_entry(fs, &virtio_fs_instances, list) {
		if (strcmp(fs->tag, tag) == 0) {
			kobject_get(&fs->kobj);
			goto found;
		}
	}

	fs = NULL; /* not found */

found:
	mutex_unlock(&virtio_fs_mutex);

	return fs;
}

static void virtio_fs_free_devs(struct virtio_fs *fs)
{
	unsigned int i;

	for (i = 0; i < fs->nvqs; i++) {
		struct virtio_fs_vq *fsvq = &fs->vqs[i];

		if (!fsvq->fud)
			continue;

		fuse_dev_free(fsvq->fud);
		fsvq->fud = NULL;
	}
}

/* Read filesystem name from virtio config into fs->tag (must kfree()). */
static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs)
{
	char tag_buf[sizeof_field(struct virtio_fs_config, tag)];
	char *end;
	size_t len;

	virtio_cread_bytes(vdev, offsetof(struct virtio_fs_config, tag),
			   &tag_buf, sizeof(tag_buf));
	end = memchr(tag_buf, '\0', sizeof(tag_buf));
	if (end == tag_buf)
		return -EINVAL; /* empty tag */
	if (!end)
		end = &tag_buf[sizeof(tag_buf)];

	len = end - tag_buf;
	fs->tag = devm_kmalloc(&vdev->dev, len + 1, GFP_KERNEL);
	if (!fs->tag)
		return -ENOMEM;
	memcpy(fs->tag, tag_buf, len);
	fs->tag[len] = '\0';

	/* While the VIRTIO specification allows any character, newlines are
	 * awkward on mount(8) command-lines and cause problems in the sysfs
	 * "tag" attr and uevent TAG= properties. Forbid them.
	 */
	if (strchr(fs->tag, '\n')) {
		dev_dbg(&vdev->dev, "refusing virtiofs tag with newline character\n");
		return -EINVAL;
	}

	return 0;
}

/* Work function for hiprio completion */
static void virtio_fs_hiprio_done_work(struct work_struct *work)
{
	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
						 done_work);
	struct virtqueue *vq = fsvq->vq;

	/* Free completed FUSE_FORGET requests */
	spin_lock(&fsvq->lock);
	do {
		unsigned int len;
		void *req;

		virtqueue_disable_cb(vq);

		while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
			kfree(req);
			dec_in_flight_req(fsvq);
		}
	} while (!virtqueue_enable_cb(vq));

	if (!list_empty(&fsvq->queued_reqs))
		schedule_work(&fsvq->dispatch_work);

	spin_unlock(&fsvq->lock);
}

static void virtio_fs_request_dispatch_work(struct work_struct *work)
{
	struct fuse_req *req;
	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
						 dispatch_work);
	int ret;

	pr_debug("virtio-fs: worker %s called.\n", __func__);
	while (1) {
		spin_lock(&fsvq->lock);
		req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req,
					       list);
		if (!req) {
			spin_unlock(&fsvq->lock);
			break;
		}

		list_del_init(&req->list);
		spin_unlock(&fsvq->lock);
		fuse_request_end(req);
	}

	/* Dispatch pending requests */
	while (1) {
		spin_lock(&fsvq->lock);
		req = list_first_entry_or_null(&fsvq->queued_reqs,
					       struct fuse_req, list);
		if (!req) {
			spin_unlock(&fsvq->lock);
			return;
		}
		list_del_init(&req->list);
		spin_unlock(&fsvq->lock);

		ret = virtio_fs_enqueue_req(fsvq, req, true);
		if (ret < 0) {
			if (ret == -ENOSPC) {
				spin_lock(&fsvq->lock);
				list_add_tail(&req->list, &fsvq->queued_reqs);
				spin_unlock(&fsvq->lock);
				return;
			}
			req->out.h.error = ret;
			spin_lock(&fsvq->lock);
			dec_in_flight_req(fsvq);
			spin_unlock(&fsvq->lock);
			pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n",
			       ret);
			fuse_request_end(req);
		}
	}
}

/*
 * Returns 1 if queue is full and sender should wait a bit before sending
 * next request, 0 otherwise.
 */
static int send_forget_request(struct virtio_fs_vq *fsvq,
			       struct virtio_fs_forget *forget,
			       bool in_flight)
{
	struct scatterlist sg;
	struct virtqueue *vq;
	int ret = 0;
	bool notify;
	struct virtio_fs_forget_req *req = &forget->req;

	spin_lock(&fsvq->lock);
	if (!fsvq->connected) {
		if (in_flight)
			dec_in_flight_req(fsvq);
		kfree(forget);
		goto out;
	}

	sg_init_one(&sg, req, sizeof(*req));
	vq = fsvq->vq;
	dev_dbg(&vq->vdev->dev, "%s\n", __func__);

	ret = virtqueue_add_outbuf(vq, &sg, 1, forget, GFP_ATOMIC);
	if (ret < 0) {
		if (ret == -ENOSPC) {
			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n",
				 ret);
			list_add_tail(&forget->list, &fsvq->queued_reqs);
			if (!in_flight)
				inc_in_flight_req(fsvq);
			/* Queue is full */
			ret = 1;
		} else {
			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
				 ret);
			kfree(forget);
			if (in_flight)
				dec_in_flight_req(fsvq);
		}
		goto out;
	}

	if (!in_flight)
		inc_in_flight_req(fsvq);
	notify = virtqueue_kick_prepare(vq);
	spin_unlock(&fsvq->lock);

	if (notify)
		virtqueue_notify(vq);
	return ret;
out:
	spin_unlock(&fsvq->lock);
	return ret;
}

static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
{
	struct virtio_fs_forget *forget;
	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
						 dispatch_work);
	pr_debug("virtio-fs: worker %s called.\n", __func__);
	while (1) {
		spin_lock(&fsvq->lock);
		forget = list_first_entry_or_null(&fsvq->queued_reqs,
					struct virtio_fs_forget, list);
		if (!forget) {
			spin_unlock(&fsvq->lock);
			return;
		}

		list_del(&forget->list);
		spin_unlock(&fsvq->lock);
		if (send_forget_request(fsvq, forget, true))
			return;
	}
}

/* Allocate and copy args into req->argbuf */
static int copy_args_to_argbuf(struct fuse_req *req)
{
	struct fuse_args *args = req->args;
	unsigned int offset = 0;
	unsigned int num_in;
	unsigned int num_out;
	unsigned int len;
	unsigned int i;

	num_in = args->in_numargs - args->in_pages;
	num_out = args->out_numargs - args->out_pages;
	len = fuse_len_args(num_in, (struct fuse_arg *) args->in_args) +
	      fuse_len_args(num_out, args->out_args);

	req->argbuf = kmalloc(len, GFP_ATOMIC);
	if (!req->argbuf)
		return -ENOMEM;

	for (i = 0; i < num_in; i++) {
		memcpy(req->argbuf + offset,
		       args->in_args[i].value,
		       args->in_args[i].size);
		offset += args->in_args[i].size;
	}

	return 0;
}

/* Copy args out of and free req->argbuf */
static void copy_args_from_argbuf(struct fuse_args *args, struct fuse_req *req)
{
	unsigned int remaining;
	unsigned int offset;
	unsigned int num_in;
	unsigned int num_out;
	unsigned int i;

	remaining = req->out.h.len - sizeof(req->out.h);
	num_in = args->in_numargs - args->in_pages;
	num_out = args->out_numargs - args->out_pages;
	offset = fuse_len_args(num_in, (struct fuse_arg *)args->in_args);

	for (i = 0; i < num_out; i++) {
		unsigned int argsize = args->out_args[i].size;

		if (args->out_argvar &&
		    i == args->out_numargs - 1 &&
		    argsize > remaining) {
			argsize = remaining;
		}

		memcpy(args->out_args[i].value, req->argbuf + offset, argsize);
		offset += argsize;

		if (i != args->out_numargs - 1)
			remaining -= argsize;
	}

	/* Store the actual size of the variable-length arg */
	if (args->out_argvar)
		args->out_args[args->out_numargs - 1].size = remaining;

	kfree(req->argbuf);
	req->argbuf = NULL;
}

/* Work function for request completion */
static void virtio_fs_request_complete(struct fuse_req *req,
				       struct virtio_fs_vq *fsvq)
{
	struct fuse_pqueue *fpq = &fsvq->fud->pq;
	struct fuse_args *args;
	struct fuse_args_pages *ap;
	unsigned int len, i, thislen;
	struct page *page;

	/*
	 * TODO verify that server properly follows FUSE protocol
	 * (oh.uniq, oh.len)
	 */
	args = req->args;
	copy_args_from_argbuf(args, req);

	if (args->out_pages && args->page_zeroing) {
		len = args->out_args[args->out_numargs - 1].size;
		ap = container_of(args, typeof(*ap), args);
		for (i = 0; i < ap->num_pages; i++) {
			thislen = ap->descs[i].length;
			if (len < thislen) {
				WARN_ON(ap->descs[i].offset);
				page = ap->pages[i];
				zero_user_segment(page, len, thislen);
				len = 0;
			} else {
				len -= thislen;
			}
		}
	}

	spin_lock(&fpq->lock);
	clear_bit(FR_SENT, &req->flags);
	spin_unlock(&fpq->lock);

	fuse_request_end(req);
	spin_lock(&fsvq->lock);
	dec_in_flight_req(fsvq);
	spin_unlock(&fsvq->lock);
}

static void virtio_fs_complete_req_work(struct work_struct *work)
{
	struct virtio_fs_req_work *w =
		container_of(work, typeof(*w), done_work);

	virtio_fs_request_complete(w->req, w->fsvq);
	kfree(w);
}

static void virtio_fs_requests_done_work(struct work_struct *work)
{
	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
						 done_work);
	struct fuse_pqueue *fpq = &fsvq->fud->pq;
	struct virtqueue *vq = fsvq->vq;
	struct fuse_req *req;
	struct fuse_req *next;
	unsigned int len;
	LIST_HEAD(reqs);

	/* Collect completed requests off the virtqueue */
	spin_lock(&fsvq->lock);
	do {
		virtqueue_disable_cb(vq);

		while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
			spin_lock(&fpq->lock);
			list_move_tail(&req->list, &reqs);
			spin_unlock(&fpq->lock);
		}
	} while (!virtqueue_enable_cb(vq));
	spin_unlock(&fsvq->lock);

	/* End requests */
	list_for_each_entry_safe(req, next, &reqs, list) {
		list_del_init(&req->list);

		/* blocking async request completes in a worker context */
		if (req->args->may_block) {
			struct virtio_fs_req_work *w;

			w = kzalloc(sizeof(*w), GFP_NOFS | __GFP_NOFAIL);
			INIT_WORK(&w->done_work, virtio_fs_complete_req_work);
			w->fsvq = fsvq;
			w->req = req;
			schedule_work(&w->done_work);
		} else {
			virtio_fs_request_complete(req, fsvq);
		}
	}

	/* Try to push previously queued requests, as the queue might no longer be full */
	spin_lock(&fsvq->lock);
	if (!list_empty(&fsvq->queued_reqs))
		schedule_work(&fsvq->dispatch_work);
	spin_unlock(&fsvq->lock);
}

static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs)
{
	const struct cpumask *mask, *masks;
	unsigned int q, cpu;

	/* First attempt to map using existing transport layer affinities
	 * e.g. PCIe MSI-X
	 */
	if (!vdev->config->get_vq_affinity)
		goto fallback;

	for (q = 0; q < fs->num_request_queues; q++) {
		mask = vdev->config->get_vq_affinity(vdev, VQ_REQUEST + q);
		if (!mask)
			goto fallback;

		for_each_cpu(cpu, mask)
			fs->mq_map[cpu] = q;
	}

	return;
fallback:
	/* Attempt to map evenly in groups over the CPUs */
	masks = group_cpus_evenly(fs->num_request_queues);
	/* If even this fails we default to all CPUs use queue zero */
	if (!masks) {
		for_each_possible_cpu(cpu)
			fs->mq_map[cpu] = 0;
		return;
	}

	for (q = 0; q < fs->num_request_queues; q++) {
		for_each_cpu(cpu, &masks[q])
			fs->mq_map[cpu] = q;
	}
	kfree(masks);
}

/* Virtqueue interrupt handler */
static void virtio_fs_vq_done(struct virtqueue *vq)
{
	struct virtio_fs_vq *fsvq = vq_to_fsvq(vq);

	dev_dbg(&vq->vdev->dev, "%s %s\n", __func__, fsvq->name);

	schedule_work(&fsvq->done_work);
}

static void virtio_fs_init_vq(struct virtio_fs_vq *fsvq, char *name,
			      int vq_type)
{
	strscpy(fsvq->name, name, VQ_NAME_LEN);
	spin_lock_init(&fsvq->lock);
	INIT_LIST_HEAD(&fsvq->queued_reqs);
	INIT_LIST_HEAD(&fsvq->end_reqs);
	init_completion(&fsvq->in_flight_zero);

	if (vq_type == VQ_REQUEST) {
		INIT_WORK(&fsvq->done_work, virtio_fs_requests_done_work);
		INIT_WORK(&fsvq->dispatch_work,
				virtio_fs_request_dispatch_work);
	} else {
		INIT_WORK(&fsvq->done_work, virtio_fs_hiprio_done_work);
		INIT_WORK(&fsvq->dispatch_work,
				virtio_fs_hiprio_dispatch_work);
	}
}

/* Initialize virtqueues */
static int virtio_fs_setup_vqs(struct virtio_device *vdev,
			       struct virtio_fs *fs)
{
	struct virtqueue_info *vqs_info;
	struct virtqueue **vqs;
	/* Specify pre_vectors to ensure that the queues before the
	 * request queues (e.g. hiprio) don't claim any of the CPUs in
	 * the multi-queue mapping and interrupt affinities
	 */
	struct irq_affinity desc = { .pre_vectors = VQ_REQUEST };
	unsigned int i;
	int ret = 0;

	virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues,
			&fs->num_request_queues);
	if (fs->num_request_queues == 0)
		return -EINVAL;

	/* Truncate nr of request queues to nr_cpu_id */
	fs->num_request_queues = min_t(unsigned int, fs->num_request_queues,
					nr_cpu_ids);
	fs->nvqs = VQ_REQUEST + fs->num_request_queues;
	fs->vqs = kcalloc(fs->nvqs, sizeof(fs->vqs[VQ_HIPRIO]), GFP_KERNEL);
	if (!fs->vqs)
		return -ENOMEM;

	vqs = kmalloc_array(fs->nvqs, sizeof(vqs[VQ_HIPRIO]), GFP_KERNEL);
	fs->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*fs->mq_map), GFP_KERNEL,
					dev_to_node(&vdev->dev));
	vqs_info = kcalloc(fs->nvqs, sizeof(*vqs_info), GFP_KERNEL);
	if (!vqs || !vqs_info || !fs->mq_map) {
		ret = -ENOMEM;
		goto out;
	}

	/* Initialize the hiprio/forget request virtqueue */
	vqs_info[VQ_HIPRIO].callback = virtio_fs_vq_done;
	virtio_fs_init_vq(&fs->vqs[VQ_HIPRIO], "hiprio", VQ_HIPRIO);
	vqs_info[VQ_HIPRIO].name = fs->vqs[VQ_HIPRIO].name;

	/* Initialize the requests virtqueues */
	for (i = VQ_REQUEST; i < fs->nvqs; i++) {
		char vq_name[VQ_NAME_LEN];

		snprintf(vq_name, VQ_NAME_LEN, "requests.%u", i - VQ_REQUEST);
		virtio_fs_init_vq(&fs->vqs[i], vq_name, VQ_REQUEST);
		vqs_info[i].callback = virtio_fs_vq_done;
		vqs_info[i].name = fs->vqs[i].name;
	}

	ret = virtio_find_vqs(vdev, fs->nvqs, vqs, vqs_info, &desc);
	if (ret < 0)
		goto out;

	for (i = 0; i < fs->nvqs; i++)
		fs->vqs[i].vq = vqs[i];

	virtio_fs_start_all_queues(fs);
out:
	kfree(vqs_info);
	kfree(vqs);
	if (ret) {
		kfree(fs->vqs);
		kfree(fs->mq_map);
	}
	return ret;
}

/* Free virtqueues (device must already be reset) */
static void virtio_fs_cleanup_vqs(struct virtio_device *vdev)
{
	vdev->config->del_vqs(vdev);
}

/* Map a window offset to a page frame number.  The window offset will have
 * been produced by .iomap_begin(), which maps a file offset to a window
 * offset.
 */
static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
				    long nr_pages, enum dax_access_mode mode,
				    void **kaddr, pfn_t *pfn)
{
	struct virtio_fs *fs = dax_get_private(dax_dev);
	phys_addr_t offset = PFN_PHYS(pgoff);
	size_t max_nr_pages = fs->window_len / PAGE_SIZE - pgoff;

	if (kaddr)
		*kaddr = fs->window_kaddr + offset;
	if (pfn)
		*pfn = phys_to_pfn_t(fs->window_phys_addr + offset,
					PFN_DEV | PFN_MAP);
	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
}

static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
				     pgoff_t pgoff, size_t nr_pages)
{
	long rc;
	void *kaddr;

	rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS, &kaddr,
			       NULL);
	if (rc < 0)
		return dax_mem2blk_err(rc);

	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
	dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT);
	return 0;
}

static const struct dax_operations virtio_fs_dax_ops = {
	.direct_access = virtio_fs_direct_access,
	.zero_page_range = virtio_fs_zero_page_range,
};

static void virtio_fs_cleanup_dax(void *data)
{
	struct dax_device *dax_dev = data;

	kill_dax(dax_dev);
	put_dax(dax_dev);
}

DEFINE_FREE(cleanup_dax, struct dax_dev *, if (!IS_ERR_OR_NULL(_T)) virtio_fs_cleanup_dax(_T))

static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
{
	struct dax_device *dax_dev __free(cleanup_dax) = NULL;
	struct virtio_shm_region cache_reg;
	struct dev_pagemap *pgmap;
	bool have_cache;

	if (!IS_ENABLED(CONFIG_FUSE_DAX))
		return 0;

	dax_dev = alloc_dax(fs, &virtio_fs_dax_ops);
	if (IS_ERR(dax_dev)) {
		int rc = PTR_ERR(dax_dev);
		return rc == -EOPNOTSUPP ? 0 : rc;
	}

	/* Get cache region */
	have_cache = virtio_get_shm_region(vdev, &cache_reg,
					   (u8)VIRTIO_FS_SHMCAP_ID_CACHE);
	if (!have_cache) {
		dev_notice(&vdev->dev, "%s: No cache capability\n", __func__);
		return 0;
	}

	if (!devm_request_mem_region(&vdev->dev, cache_reg.addr, cache_reg.len,
				     dev_name(&vdev->dev))) {
		dev_warn(&vdev->dev, "could not reserve region addr=0x%llx len=0x%llx\n",
			 cache_reg.addr, cache_reg.len);
		return -EBUSY;
	}

	dev_notice(&vdev->dev, "Cache len: 0x%llx @ 0x%llx\n", cache_reg.len,
		   cache_reg.addr);

	pgmap = devm_kzalloc(&vdev->dev, sizeof(*pgmap), GFP_KERNEL);
	if (!pgmap)
		return -ENOMEM;

	pgmap->type = MEMORY_DEVICE_FS_DAX;

	/* Ideally we would directly use the PCI BAR resource but
	 * devm_memremap_pages() wants its own copy in pgmap.  So
	 * initialize a struct resource from scratch (only the start
	 * and end fields will be used).
	 */
	pgmap->range = (struct range) {
		.start = (phys_addr_t) cache_reg.addr,
		.end = (phys_addr_t) cache_reg.addr + cache_reg.len - 1,
	};
	pgmap->nr_range = 1;

	fs->window_kaddr = devm_memremap_pages(&vdev->dev, pgmap);
	if (IS_ERR(fs->window_kaddr))
		return PTR_ERR(fs->window_kaddr);

	fs->window_phys_addr = (phys_addr_t) cache_reg.addr;
	fs->window_len = (phys_addr_t) cache_reg.len;

	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
		__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);

	fs->dax_dev = no_free_ptr(dax_dev);
	return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax,
					fs->dax_dev);
}

static int virtio_fs_probe(struct virtio_device *vdev)
{
	struct virtio_fs *fs;
	int ret;

	fs = kzalloc(sizeof(*fs), GFP_KERNEL);
	if (!fs)
		return -ENOMEM;
	kobject_init(&fs->kobj, &virtio_fs_ktype);
	vdev->priv = fs;

	ret = virtio_fs_read_tag(vdev, fs);
	if (ret < 0)
		goto out;

	ret = virtio_fs_setup_vqs(vdev, fs);
	if (ret < 0)
		goto out;

	virtio_fs_map_queues(vdev, fs);

	ret = virtio_fs_setup_dax(vdev, fs);
	if (ret < 0)
		goto out_vqs;

	/* Bring the device online in case the filesystem is mounted and
	 * requests need to be sent before we return.
	 */
	virtio_device_ready(vdev);

	ret = virtio_fs_add_instance(vdev, fs);
	if (ret < 0)
		goto out_vqs;

	return 0;

out_vqs:
	virtio_reset_device(vdev);
	virtio_fs_cleanup_vqs(vdev);

out:
	vdev->priv = NULL;
	kobject_put(&fs->kobj);
	return ret;
}

static void virtio_fs_stop_all_queues(struct virtio_fs *fs)
{
	struct virtio_fs_vq *fsvq;
	int i;

	for (i = 0; i < fs->nvqs; i++) {
		fsvq = &fs->vqs[i];
		spin_lock(&fsvq->lock);
		fsvq->connected = false;
		spin_unlock(&fsvq->lock);
	}
}

static void virtio_fs_remove(struct virtio_device *vdev)
{
	struct virtio_fs *fs = vdev->priv;

	mutex_lock(&virtio_fs_mutex);
	/* This device is going away. No one should get new reference */
	list_del_init(&fs->list);
	sysfs_remove_link(&fs->kobj, "device");
	kobject_del(&fs->kobj);
	virtio_fs_stop_all_queues(fs);
	virtio_fs_drain_all_queues_locked(fs);
	virtio_reset_device(vdev);
	virtio_fs_cleanup_vqs(vdev);

	vdev->priv = NULL;
	/* Put device reference on virtio_fs object */
	virtio_fs_put(fs);
	mutex_unlock(&virtio_fs_mutex);
}

#ifdef CONFIG_PM_SLEEP
static int virtio_fs_freeze(struct virtio_device *vdev)
{
	/* TODO need to save state here */
	pr_warn("virtio-fs: suspend/resume not yet supported\n");
	return -EOPNOTSUPP;
}

static int virtio_fs_restore(struct virtio_device *vdev)
{
	 /* TODO need to restore state here */
	return 0;
}
#endif /* CONFIG_PM_SLEEP */

static const struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_FS, VIRTIO_DEV_ANY_ID },
	{},
};

static const unsigned int feature_table[] = {};

static struct virtio_driver virtio_fs_driver = {
	.driver.name		= KBUILD_MODNAME,
	.id_table		= id_table,
	.feature_table		= feature_table,
	.feature_table_size	= ARRAY_SIZE(feature_table),
	.probe			= virtio_fs_probe,
	.remove			= virtio_fs_remove,
#ifdef CONFIG_PM_SLEEP
	.freeze			= virtio_fs_freeze,
	.restore		= virtio_fs_restore,
#endif
};

static void virtio_fs_wake_forget_and_unlock(struct fuse_iqueue *fiq)
__releases(fiq->lock)
{
	struct fuse_forget_link *link;
	struct virtio_fs_forget *forget;
	struct virtio_fs_forget_req *req;
	struct virtio_fs *fs;
	struct virtio_fs_vq *fsvq;
	u64 unique;

	link = fuse_dequeue_forget(fiq, 1, NULL);
	unique = fuse_get_unique(fiq);

	fs = fiq->priv;
	fsvq = &fs->vqs[VQ_HIPRIO];
	spin_unlock(&fiq->lock);

	/* Allocate a buffer for the request */
	forget = kmalloc(sizeof(*forget), GFP_NOFS | __GFP_NOFAIL);
	req = &forget->req;

	req->ih = (struct fuse_in_header){
		.opcode = FUSE_FORGET,
		.nodeid = link->forget_one.nodeid,
		.unique = unique,
		.len = sizeof(*req),
	};
	req->arg = (struct fuse_forget_in){
		.nlookup = link->forget_one.nlookup,
	};

	send_forget_request(fsvq, forget, false);
	kfree(link);
}

static void virtio_fs_wake_interrupt_and_unlock(struct fuse_iqueue *fiq)
__releases(fiq->lock)
{
	/*
	 * TODO interrupts.
	 *
	 * Normal fs operations on a local filesystems aren't interruptible.
	 * Exceptions are blocking lock operations; for example fcntl(F_SETLKW)
	 * with shared lock between host and guest.
	 */
	spin_unlock(&fiq->lock);
}

/* Count number of scatter-gather elements required */
static unsigned int sg_count_fuse_pages(struct fuse_page_desc *page_descs,
				       unsigned int num_pages,
				       unsigned int total_len)
{
	unsigned int i;
	unsigned int this_len;

	for (i = 0; i < num_pages && total_len; i++) {
		this_len =  min(page_descs[i].length, total_len);
		total_len -= this_len;
	}

	return i;
}

/* Return the number of scatter-gather list elements required */
static unsigned int sg_count_fuse_req(struct fuse_req *req)
{
	struct fuse_args *args = req->args;
	struct fuse_args_pages *ap = container_of(args, typeof(*ap), args);
	unsigned int size, total_sgs = 1 /* fuse_in_header */;

	if (args->in_numargs - args->in_pages)
		total_sgs += 1;

	if (args->in_pages) {
		size = args->in_args[args->in_numargs - 1].size;
		total_sgs += sg_count_fuse_pages(ap->descs, ap->num_pages,
						 size);
	}

	if (!test_bit(FR_ISREPLY, &req->flags))
		return total_sgs;

	total_sgs += 1 /* fuse_out_header */;

	if (args->out_numargs - args->out_pages)
		total_sgs += 1;

	if (args->out_pages) {
		size = args->out_args[args->out_numargs - 1].size;
		total_sgs += sg_count_fuse_pages(ap->descs, ap->num_pages,
						 size);
	}

	return total_sgs;
}

/* Add pages to scatter-gather list and return number of elements used */
static unsigned int sg_init_fuse_pages(struct scatterlist *sg,
				       struct page **pages,
				       struct fuse_page_desc *page_descs,
				       unsigned int num_pages,
				       unsigned int total_len)
{
	unsigned int i;
	unsigned int this_len;

	for (i = 0; i < num_pages && total_len; i++) {
		sg_init_table(&sg[i], 1);
		this_len =  min(page_descs[i].length, total_len);
		sg_set_page(&sg[i], pages[i], this_len, page_descs[i].offset);
		total_len -= this_len;
	}

	return i;
}

/* Add args to scatter-gather list and return number of elements used */
static unsigned int sg_init_fuse_args(struct scatterlist *sg,
				      struct fuse_req *req,
				      struct fuse_arg *args,
				      unsigned int numargs,
				      bool argpages,
				      void *argbuf,
				      unsigned int *len_used)
{
	struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args);
	unsigned int total_sgs = 0;
	unsigned int len;

	len = fuse_len_args(numargs - argpages, args);
	if (len)
		sg_init_one(&sg[total_sgs++], argbuf, len);

	if (argpages)
		total_sgs += sg_init_fuse_pages(&sg[total_sgs],
						ap->pages, ap->descs,
						ap->num_pages,
						args[numargs - 1].size);

	if (len_used)
		*len_used = len;

	return total_sgs;
}

/* Add a request to a virtqueue and kick the device */
static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
				 struct fuse_req *req, bool in_flight)
{
	/* requests need at least 4 elements */
	struct scatterlist *stack_sgs[6];
	struct scatterlist stack_sg[ARRAY_SIZE(stack_sgs)];
	struct scatterlist **sgs = stack_sgs;
	struct scatterlist *sg = stack_sg;
	struct virtqueue *vq;
	struct fuse_args *args = req->args;
	unsigned int argbuf_used = 0;
	unsigned int out_sgs = 0;
	unsigned int in_sgs = 0;
	unsigned int total_sgs;
	unsigned int i;
	int ret;
	bool notify;
	struct fuse_pqueue *fpq;

	/* Does the sglist fit on the stack? */
	total_sgs = sg_count_fuse_req(req);
	if (total_sgs > ARRAY_SIZE(stack_sgs)) {
		sgs = kmalloc_array(total_sgs, sizeof(sgs[0]), GFP_ATOMIC);
		sg = kmalloc_array(total_sgs, sizeof(sg[0]), GFP_ATOMIC);
		if (!sgs || !sg) {
			ret = -ENOMEM;
			goto out;
		}
	}

	/* Use a bounce buffer since stack args cannot be mapped */
	ret = copy_args_to_argbuf(req);
	if (ret < 0)
		goto out;

	/* Request elements */
	sg_init_one(&sg[out_sgs++], &req->in.h, sizeof(req->in.h));
	out_sgs += sg_init_fuse_args(&sg[out_sgs], req,
				     (struct fuse_arg *)args->in_args,
				     args->in_numargs, args->in_pages,
				     req->argbuf, &argbuf_used);

	/* Reply elements */
	if (test_bit(FR_ISREPLY, &req->flags)) {
		sg_init_one(&sg[out_sgs + in_sgs++],
			    &req->out.h, sizeof(req->out.h));
		in_sgs += sg_init_fuse_args(&sg[out_sgs + in_sgs], req,
					    args->out_args, args->out_numargs,
					    args->out_pages,
					    req->argbuf + argbuf_used, NULL);
	}

	WARN_ON(out_sgs + in_sgs != total_sgs);

	for (i = 0; i < total_sgs; i++)
		sgs[i] = &sg[i];

	spin_lock(&fsvq->lock);

	if (!fsvq->connected) {
		spin_unlock(&fsvq->lock);
		ret = -ENOTCONN;
		goto out;
	}

	vq = fsvq->vq;
	ret = virtqueue_add_sgs(vq, sgs, out_sgs, in_sgs, req, GFP_ATOMIC);
	if (ret < 0) {
		spin_unlock(&fsvq->lock);
		goto out;
	}

	/* Request successfully sent. */
	fpq = &fsvq->fud->pq;
	spin_lock(&fpq->lock);
	list_add_tail(&req->list, fpq->processing);
	spin_unlock(&fpq->lock);
	set_bit(FR_SENT, &req->flags);
	/* matches barrier in request_wait_answer() */
	smp_mb__after_atomic();

	if (!in_flight)
		inc_in_flight_req(fsvq);
	notify = virtqueue_kick_prepare(vq);

	spin_unlock(&fsvq->lock);

	if (notify)
		virtqueue_notify(vq);

out:
	if (ret < 0 && req->argbuf) {
		kfree(req->argbuf);
		req->argbuf = NULL;
	}
	if (sgs != stack_sgs) {
		kfree(sgs);
		kfree(sg);
	}

	return ret;
}

static void virtio_fs_wake_pending_and_unlock(struct fuse_iqueue *fiq)
__releases(fiq->lock)
{
	unsigned int queue_id;
	struct virtio_fs *fs;
	struct fuse_req *req;
	struct virtio_fs_vq *fsvq;
	int ret;

	WARN_ON(list_empty(&fiq->pending));
	req = list_last_entry(&fiq->pending, struct fuse_req, list);
	clear_bit(FR_PENDING, &req->flags);
	list_del_init(&req->list);
	WARN_ON(!list_empty(&fiq->pending));
	spin_unlock(&fiq->lock);

	fs = fiq->priv;
	queue_id = VQ_REQUEST + fs->mq_map[raw_smp_processor_id()];

	pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u queue_id %u\n",
		 __func__, req->in.h.opcode, req->in.h.unique,
		 req->in.h.nodeid, req->in.h.len,
		 fuse_len_args(req->args->out_numargs, req->args->out_args),
		 queue_id);

	fsvq = &fs->vqs[queue_id];
	ret = virtio_fs_enqueue_req(fsvq, req, false);
	if (ret < 0) {
		if (ret == -ENOSPC) {
			/*
			 * Virtqueue full. Retry submission from worker
			 * context as we might be holding fc->bg_lock.
			 */
			spin_lock(&fsvq->lock);
			list_add_tail(&req->list, &fsvq->queued_reqs);
			inc_in_flight_req(fsvq);
			spin_unlock(&fsvq->lock);
			return;
		}
		req->out.h.error = ret;
		pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret);

		/* Can't end request in submission context. Use a worker */
		spin_lock(&fsvq->lock);
		list_add_tail(&req->list, &fsvq->end_reqs);
		schedule_work(&fsvq->dispatch_work);
		spin_unlock(&fsvq->lock);
		return;
	}
}

static const struct fuse_iqueue_ops virtio_fs_fiq_ops = {
	.wake_forget_and_unlock		= virtio_fs_wake_forget_and_unlock,
	.wake_interrupt_and_unlock	= virtio_fs_wake_interrupt_and_unlock,
	.wake_pending_and_unlock	= virtio_fs_wake_pending_and_unlock,
	.release			= virtio_fs_fiq_release,
};

static inline void virtio_fs_ctx_set_defaults(struct fuse_fs_context *ctx)
{
	ctx->rootmode = S_IFDIR;
	ctx->default_permissions = 1;
	ctx->allow_other = 1;
	ctx->max_read = UINT_MAX;
	ctx->blksize = 512;
	ctx->destroy = true;
	ctx->no_control = true;
	ctx->no_force_umount = true;
}

static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc)
{
	struct fuse_mount *fm = get_fuse_mount_super(sb);
	struct fuse_conn *fc = fm->fc;
	struct virtio_fs *fs = fc->iq.priv;
	struct fuse_fs_context *ctx = fsc->fs_private;
	unsigned int i;
	int err;

	virtio_fs_ctx_set_defaults(ctx);
	mutex_lock(&virtio_fs_mutex);

	/* After holding mutex, make sure virtiofs device is still there.
	 * Though we are holding a reference to it, drive ->remove might
	 * still have cleaned up virtual queues. In that case bail out.
	 */
	err = -EINVAL;
	if (list_empty(&fs->list)) {
		pr_info("virtio-fs: tag <%s> not found\n", fs->tag);
		goto err;
	}

	err = -ENOMEM;
	/* Allocate fuse_dev for hiprio and notification queues */
	for (i = 0; i < fs->nvqs; i++) {
		struct virtio_fs_vq *fsvq = &fs->vqs[i];

		fsvq->fud = fuse_dev_alloc();
		if (!fsvq->fud)
			goto err_free_fuse_devs;
	}

	/* virtiofs allocates and installs its own fuse devices */
	ctx->fudptr = NULL;
	if (ctx->dax_mode != FUSE_DAX_NEVER) {
		if (ctx->dax_mode == FUSE_DAX_ALWAYS && !fs->dax_dev) {
			err = -EINVAL;
			pr_err("virtio-fs: dax can't be enabled as filesystem"
			       " device does not support it.\n");
			goto err_free_fuse_devs;
		}
		ctx->dax_dev = fs->dax_dev;
	}
	err = fuse_fill_super_common(sb, ctx);
	if (err < 0)
		goto err_free_fuse_devs;

	for (i = 0; i < fs->nvqs; i++) {
		struct virtio_fs_vq *fsvq = &fs->vqs[i];

		fuse_dev_install(fsvq->fud, fc);
	}

	/* Previous unmount will stop all queues. Start these again */
	virtio_fs_start_all_queues(fs);
	fuse_send_init(fm);
	mutex_unlock(&virtio_fs_mutex);
	return 0;

err_free_fuse_devs:
	virtio_fs_free_devs(fs);
err:
	mutex_unlock(&virtio_fs_mutex);
	return err;
}

static void virtio_fs_conn_destroy(struct fuse_mount *fm)
{
	struct fuse_conn *fc = fm->fc;
	struct virtio_fs *vfs = fc->iq.priv;
	struct virtio_fs_vq *fsvq = &vfs->vqs[VQ_HIPRIO];

	/* Stop dax worker. Soon evict_inodes() will be called which
	 * will free all memory ranges belonging to all inodes.
	 */
	if (IS_ENABLED(CONFIG_FUSE_DAX))
		fuse_dax_cancel_work(fc);

	/* Stop forget queue. Soon destroy will be sent */
	spin_lock(&fsvq->lock);
	fsvq->connected = false;
	spin_unlock(&fsvq->lock);
	virtio_fs_drain_all_queues(vfs);

	fuse_conn_destroy(fm);

	/* fuse_conn_destroy() must have sent destroy. Stop all queues
	 * and drain one more time and free fuse devices. Freeing fuse
	 * devices will drop their reference on fuse_conn and that in
	 * turn will drop its reference on virtio_fs object.
	 */
	virtio_fs_stop_all_queues(vfs);
	virtio_fs_drain_all_queues(vfs);
	virtio_fs_free_devs(vfs);
}

static void virtio_kill_sb(struct super_block *sb)
{
	struct fuse_mount *fm = get_fuse_mount_super(sb);
	bool last;

	/* If mount failed, we can still be called without any fc */
	if (sb->s_root) {
		last = fuse_mount_remove(fm);
		if (last)
			virtio_fs_conn_destroy(fm);
	}
	kill_anon_super(sb);
	fuse_mount_destroy(fm);
}

static int virtio_fs_test_super(struct super_block *sb,
				struct fs_context *fsc)
{
	struct fuse_mount *fsc_fm = fsc->s_fs_info;
	struct fuse_mount *sb_fm = get_fuse_mount_super(sb);

	return fsc_fm->fc->iq.priv == sb_fm->fc->iq.priv;
}

static int virtio_fs_get_tree(struct fs_context *fsc)
{
	struct virtio_fs *fs;
	struct super_block *sb;
	struct fuse_conn *fc = NULL;
	struct fuse_mount *fm;
	unsigned int virtqueue_size;
	int err = -EIO;

	/* This gets a reference on virtio_fs object. This ptr gets installed
	 * in fc->iq->priv. Once fuse_conn is going away, it calls ->put()
	 * to drop the reference to this object.
	 */
	fs = virtio_fs_find_instance(fsc->source);
	if (!fs) {
		pr_info("virtio-fs: tag <%s> not found\n", fsc->source);
		return -EINVAL;
	}

	virtqueue_size = virtqueue_get_vring_size(fs->vqs[VQ_REQUEST].vq);
	if (WARN_ON(virtqueue_size <= FUSE_HEADER_OVERHEAD))
		goto out_err;

	err = -ENOMEM;
	fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL);
	if (!fc)
		goto out_err;

	fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL);
	if (!fm)
		goto out_err;

	fuse_conn_init(fc, fm, fsc->user_ns, &virtio_fs_fiq_ops, fs);
	fc->release = fuse_free_conn;
	fc->delete_stale = true;
	fc->auto_submounts = true;
	fc->sync_fs = true;

	/* Tell FUSE to split requests that exceed the virtqueue's size */
	fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit,
				    virtqueue_size - FUSE_HEADER_OVERHEAD);

	fsc->s_fs_info = fm;
	sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc);
	if (fsc->s_fs_info)
		fuse_mount_destroy(fm);
	if (IS_ERR(sb))
		return PTR_ERR(sb);

	if (!sb->s_root) {
		err = virtio_fs_fill_super(sb, fsc);
		if (err) {
			deactivate_locked_super(sb);
			return err;
		}

		sb->s_flags |= SB_ACTIVE;
	}

	WARN_ON(fsc->root);
	fsc->root = dget(sb->s_root);
	return 0;

out_err:
	kfree(fc);
	mutex_lock(&virtio_fs_mutex);
	virtio_fs_put(fs);
	mutex_unlock(&virtio_fs_mutex);
	return err;
}

static const struct fs_context_operations virtio_fs_context_ops = {
	.free		= virtio_fs_free_fsc,
	.parse_param	= virtio_fs_parse_param,
	.get_tree	= virtio_fs_get_tree,
};

static int virtio_fs_init_fs_context(struct fs_context *fsc)
{
	struct fuse_fs_context *ctx;

	if (fsc->purpose == FS_CONTEXT_FOR_SUBMOUNT)
		return fuse_init_fs_context_submount(fsc);

	ctx = kzalloc(sizeof(struct fuse_fs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;
	fsc->fs_private = ctx;
	fsc->ops = &virtio_fs_context_ops;
	return 0;
}

static struct file_system_type virtio_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "virtiofs",
	.init_fs_context = virtio_fs_init_fs_context,
	.kill_sb	= virtio_kill_sb,
};

static int virtio_fs_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
{
	const struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj);

	add_uevent_var(env, "TAG=%s", fs->tag);
	return 0;
}

static const struct kset_uevent_ops virtio_fs_uevent_ops = {
	.uevent = virtio_fs_uevent,
};

static int __init virtio_fs_sysfs_init(void)
{
	virtio_fs_kset = kset_create_and_add("virtiofs", &virtio_fs_uevent_ops,
					     fs_kobj);
	if (!virtio_fs_kset)
		return -ENOMEM;
	return 0;
}

static void virtio_fs_sysfs_exit(void)
{
	kset_unregister(virtio_fs_kset);
	virtio_fs_kset = NULL;
}

static int __init virtio_fs_init(void)
{
	int ret;

	ret = virtio_fs_sysfs_init();
	if (ret < 0)
		return ret;

	ret = register_virtio_driver(&virtio_fs_driver);
	if (ret < 0)
		goto sysfs_exit;

	ret = register_filesystem(&virtio_fs_type);
	if (ret < 0)
		goto unregister_virtio_driver;

	return 0;

unregister_virtio_driver:
	unregister_virtio_driver(&virtio_fs_driver);
sysfs_exit:
	virtio_fs_sysfs_exit();
	return ret;
}
module_init(virtio_fs_init);

static void __exit virtio_fs_exit(void)
{
	unregister_filesystem(&virtio_fs_type);
	unregister_virtio_driver(&virtio_fs_driver);
	virtio_fs_sysfs_exit();
}
module_exit(virtio_fs_exit);

MODULE_AUTHOR("Stefan Hajnoczi <stefanha@redhat.com>");
MODULE_DESCRIPTION("Virtio Filesystem");
MODULE_LICENSE("GPL");
MODULE_ALIAS_FS(KBUILD_MODNAME);
MODULE_DEVICE_TABLE(virtio, id_table);