summaryrefslogtreecommitdiffstats
path: root/drivers/scsi/virtio_scsi.c
blob: 89ca269457211e0ecd504b3397f6236812942e72 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Virtio SCSI HBA driver
 *
 * Copyright IBM Corp. 2010
 * Copyright Red Hat, Inc. 2011
 *
 * Authors:
 *  Stefan Hajnoczi   <stefanha@linux.vnet.ibm.com>
 *  Paolo Bonzini   <pbonzini@redhat.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/mempool.h>
#include <linux/interrupt.h>
#include <linux/virtio.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
#include <linux/virtio_scsi.h>
#include <linux/cpu.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_tcq.h>
#include <scsi/scsi_devinfo.h>
#include <linux/seqlock.h>
#include <linux/blk-mq-virtio.h>

#include "sd.h"

#define VIRTIO_SCSI_MEMPOOL_SZ 64
#define VIRTIO_SCSI_EVENT_LEN 8
#define VIRTIO_SCSI_VQ_BASE 2

static unsigned int virtscsi_poll_queues;
module_param(virtscsi_poll_queues, uint, 0644);
MODULE_PARM_DESC(virtscsi_poll_queues,
		 "The number of dedicated virtqueues for polling I/O");

/* Command queue element */
struct virtio_scsi_cmd {
	struct scsi_cmnd *sc;
	struct completion *comp;
	union {
		struct virtio_scsi_cmd_req       cmd;
		struct virtio_scsi_cmd_req_pi    cmd_pi;
		struct virtio_scsi_ctrl_tmf_req  tmf;
		struct virtio_scsi_ctrl_an_req   an;
	} req;
	union {
		struct virtio_scsi_cmd_resp      cmd;
		struct virtio_scsi_ctrl_tmf_resp tmf;
		struct virtio_scsi_ctrl_an_resp  an;
		struct virtio_scsi_event         evt;
	} resp;
} ____cacheline_aligned_in_smp;

struct virtio_scsi_event_node {
	struct virtio_scsi *vscsi;
	struct virtio_scsi_event event;
	struct work_struct work;
};

struct virtio_scsi_vq {
	/* Protects vq */
	spinlock_t vq_lock;

	struct virtqueue *vq;
};

/* Driver instance state */
struct virtio_scsi {
	struct virtio_device *vdev;

	/* Get some buffers ready for event vq */
	struct virtio_scsi_event_node event_list[VIRTIO_SCSI_EVENT_LEN];

	u32 num_queues;
	int io_queues[HCTX_MAX_TYPES];

	struct hlist_node node;

	/* Protected by event_vq lock */
	bool stop_events;

	struct virtio_scsi_vq ctrl_vq;
	struct virtio_scsi_vq event_vq;
	struct virtio_scsi_vq req_vqs[];
};

static struct kmem_cache *virtscsi_cmd_cache;
static mempool_t *virtscsi_cmd_pool;

static inline struct Scsi_Host *virtio_scsi_host(struct virtio_device *vdev)
{
	return vdev->priv;
}

static void virtscsi_compute_resid(struct scsi_cmnd *sc, u32 resid)
{
	if (resid)
		scsi_set_resid(sc, min(resid, scsi_bufflen(sc)));
}

/*
 * virtscsi_complete_cmd - finish a scsi_cmd and invoke scsi_done
 *
 * Called with vq_lock held.
 */
static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
{
	struct virtio_scsi_cmd *cmd = buf;
	struct scsi_cmnd *sc = cmd->sc;
	struct virtio_scsi_cmd_resp *resp = &cmd->resp.cmd;

	dev_dbg(&sc->device->sdev_gendev,
		"cmd %p response %u status %#02x sense_len %u\n",
		sc, resp->response, resp->status, resp->sense_len);

	sc->result = resp->status;
	virtscsi_compute_resid(sc, virtio32_to_cpu(vscsi->vdev, resp->resid));
	switch (resp->response) {
	case VIRTIO_SCSI_S_OK:
		set_host_byte(sc, DID_OK);
		break;
	case VIRTIO_SCSI_S_OVERRUN:
		set_host_byte(sc, DID_ERROR);
		break;
	case VIRTIO_SCSI_S_ABORTED:
		set_host_byte(sc, DID_ABORT);
		break;
	case VIRTIO_SCSI_S_BAD_TARGET:
		set_host_byte(sc, DID_BAD_TARGET);
		break;
	case VIRTIO_SCSI_S_RESET:
		set_host_byte(sc, DID_RESET);
		break;
	case VIRTIO_SCSI_S_BUSY:
		set_host_byte(sc, DID_BUS_BUSY);
		break;
	case VIRTIO_SCSI_S_TRANSPORT_FAILURE:
		set_host_byte(sc, DID_TRANSPORT_DISRUPTED);
		break;
	case VIRTIO_SCSI_S_TARGET_FAILURE:
		set_host_byte(sc, DID_BAD_TARGET);
		break;
	case VIRTIO_SCSI_S_NEXUS_FAILURE:
		set_status_byte(sc, SAM_STAT_RESERVATION_CONFLICT);
		break;
	default:
		scmd_printk(KERN_WARNING, sc, "Unknown response %d",
			    resp->response);
		fallthrough;
	case VIRTIO_SCSI_S_FAILURE:
		set_host_byte(sc, DID_ERROR);
		break;
	}

	WARN_ON(virtio32_to_cpu(vscsi->vdev, resp->sense_len) >
		VIRTIO_SCSI_SENSE_SIZE);
	if (resp->sense_len) {
		memcpy(sc->sense_buffer, resp->sense,
		       min_t(u32,
			     virtio32_to_cpu(vscsi->vdev, resp->sense_len),
			     VIRTIO_SCSI_SENSE_SIZE));
	}

	scsi_done(sc);
}

static void virtscsi_vq_done(struct virtio_scsi *vscsi,
			     struct virtio_scsi_vq *virtscsi_vq,
			     void (*fn)(struct virtio_scsi *vscsi, void *buf))
{
	void *buf;
	unsigned int len;
	unsigned long flags;
	struct virtqueue *vq = virtscsi_vq->vq;

	spin_lock_irqsave(&virtscsi_vq->vq_lock, flags);
	do {
		virtqueue_disable_cb(vq);
		while ((buf = virtqueue_get_buf(vq, &len)) != NULL)
			fn(vscsi, buf);

	} while (!virtqueue_enable_cb(vq));
	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);
}

static void virtscsi_req_done(struct virtqueue *vq)
{
	struct Scsi_Host *sh = virtio_scsi_host(vq->vdev);
	struct virtio_scsi *vscsi = shost_priv(sh);
	int index = vq->index - VIRTIO_SCSI_VQ_BASE;
	struct virtio_scsi_vq *req_vq = &vscsi->req_vqs[index];

	virtscsi_vq_done(vscsi, req_vq, virtscsi_complete_cmd);
};

static void virtscsi_poll_requests(struct virtio_scsi *vscsi)
{
	int i, num_vqs;

	num_vqs = vscsi->num_queues;
	for (i = 0; i < num_vqs; i++)
		virtscsi_vq_done(vscsi, &vscsi->req_vqs[i],
				 virtscsi_complete_cmd);
}

static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)
{
	struct virtio_scsi_cmd *cmd = buf;

	if (cmd->comp)
		complete(cmd->comp);
}

static void virtscsi_ctrl_done(struct virtqueue *vq)
{
	struct Scsi_Host *sh = virtio_scsi_host(vq->vdev);
	struct virtio_scsi *vscsi = shost_priv(sh);

	virtscsi_vq_done(vscsi, &vscsi->ctrl_vq, virtscsi_complete_free);
};

static void virtscsi_handle_event(struct work_struct *work);

static int virtscsi_kick_event(struct virtio_scsi *vscsi,
			       struct virtio_scsi_event_node *event_node)
{
	int err;
	struct scatterlist sg;
	unsigned long flags;

	INIT_WORK(&event_node->work, virtscsi_handle_event);
	sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event));

	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);

	err = virtqueue_add_inbuf(vscsi->event_vq.vq, &sg, 1, event_node,
				  GFP_ATOMIC);
	if (!err)
		virtqueue_kick(vscsi->event_vq.vq);

	spin_unlock_irqrestore(&vscsi->event_vq.vq_lock, flags);

	return err;
}

static int virtscsi_kick_event_all(struct virtio_scsi *vscsi)
{
	int i;

	for (i = 0; i < VIRTIO_SCSI_EVENT_LEN; i++) {
		vscsi->event_list[i].vscsi = vscsi;
		virtscsi_kick_event(vscsi, &vscsi->event_list[i]);
	}

	return 0;
}

static void virtscsi_cancel_event_work(struct virtio_scsi *vscsi)
{
	int i;

	/* Stop scheduling work before calling cancel_work_sync.  */
	spin_lock_irq(&vscsi->event_vq.vq_lock);
	vscsi->stop_events = true;
	spin_unlock_irq(&vscsi->event_vq.vq_lock);

	for (i = 0; i < VIRTIO_SCSI_EVENT_LEN; i++)
		cancel_work_sync(&vscsi->event_list[i].work);
}

static void virtscsi_handle_transport_reset(struct virtio_scsi *vscsi,
					    struct virtio_scsi_event *event)
{
	struct scsi_device *sdev;
	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
	unsigned int target = event->lun[1];
	unsigned int lun = (event->lun[2] << 8) | event->lun[3];

	switch (virtio32_to_cpu(vscsi->vdev, event->reason)) {
	case VIRTIO_SCSI_EVT_RESET_RESCAN:
		if (lun == 0) {
			scsi_scan_target(&shost->shost_gendev, 0, target,
					 SCAN_WILD_CARD, SCSI_SCAN_INITIAL);
		} else {
			scsi_add_device(shost, 0, target, lun);
		}
		break;
	case VIRTIO_SCSI_EVT_RESET_REMOVED:
		sdev = scsi_device_lookup(shost, 0, target, lun);
		if (sdev) {
			scsi_remove_device(sdev);
			scsi_device_put(sdev);
		} else {
			pr_err("SCSI device %d 0 %d %d not found\n",
				shost->host_no, target, lun);
		}
		break;
	default:
		pr_info("Unsupported virtio scsi event reason %x\n", event->reason);
	}
}

static void virtscsi_handle_param_change(struct virtio_scsi *vscsi,
					 struct virtio_scsi_event *event)
{
	struct scsi_device *sdev;
	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
	unsigned int target = event->lun[1];
	unsigned int lun = (event->lun[2] << 8) | event->lun[3];
	u8 asc = virtio32_to_cpu(vscsi->vdev, event->reason) & 255;
	u8 ascq = virtio32_to_cpu(vscsi->vdev, event->reason) >> 8;

	sdev = scsi_device_lookup(shost, 0, target, lun);
	if (!sdev) {
		pr_err("SCSI device %d 0 %d %d not found\n",
			shost->host_no, target, lun);
		return;
	}

	/* Handle "Parameters changed", "Mode parameters changed", and
	   "Capacity data has changed".  */
	if (asc == 0x2a && (ascq == 0x00 || ascq == 0x01 || ascq == 0x09))
		scsi_rescan_device(sdev);

	scsi_device_put(sdev);
}

static int virtscsi_rescan_hotunplug(struct virtio_scsi *vscsi)
{
	struct scsi_device *sdev;
	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
	unsigned char scsi_cmd[MAX_COMMAND_SIZE];
	int result, inquiry_len, inq_result_len = 256;
	char *inq_result = kmalloc(inq_result_len, GFP_KERNEL);

	if (!inq_result)
		return -ENOMEM;

	shost_for_each_device(sdev, shost) {
		inquiry_len = sdev->inquiry_len ? sdev->inquiry_len : 36;

		memset(scsi_cmd, 0, sizeof(scsi_cmd));
		scsi_cmd[0] = INQUIRY;
		scsi_cmd[4] = (unsigned char) inquiry_len;

		memset(inq_result, 0, inq_result_len);

		result = scsi_execute_cmd(sdev, scsi_cmd, REQ_OP_DRV_IN,
					  inq_result, inquiry_len,
					  SD_TIMEOUT, SD_MAX_RETRIES, NULL);

		if (result == 0 && inq_result[0] >> 5) {
			/* PQ indicates the LUN is not attached */
			scsi_remove_device(sdev);
		} else if (result > 0 && host_byte(result) == DID_BAD_TARGET) {
			/*
			 * If all LUNs of a virtio-scsi device are unplugged
			 * it will respond with BAD TARGET on any INQUIRY
			 * command.
			 * Remove the device in this case as well.
			 */
			scsi_remove_device(sdev);
		}
	}

	kfree(inq_result);
	return 0;
}

static void virtscsi_handle_event(struct work_struct *work)
{
	struct virtio_scsi_event_node *event_node =
		container_of(work, struct virtio_scsi_event_node, work);
	struct virtio_scsi *vscsi = event_node->vscsi;
	struct virtio_scsi_event *event = &event_node->event;

	if (event->event &
	    cpu_to_virtio32(vscsi->vdev, VIRTIO_SCSI_T_EVENTS_MISSED)) {
		int ret;

		event->event &= ~cpu_to_virtio32(vscsi->vdev,
						   VIRTIO_SCSI_T_EVENTS_MISSED);
		ret = virtscsi_rescan_hotunplug(vscsi);
		if (ret)
			return;
		scsi_scan_host(virtio_scsi_host(vscsi->vdev));
	}

	switch (virtio32_to_cpu(vscsi->vdev, event->event)) {
	case VIRTIO_SCSI_T_NO_EVENT:
		break;
	case VIRTIO_SCSI_T_TRANSPORT_RESET:
		virtscsi_handle_transport_reset(vscsi, event);
		break;
	case VIRTIO_SCSI_T_PARAM_CHANGE:
		virtscsi_handle_param_change(vscsi, event);
		break;
	default:
		pr_err("Unsupported virtio scsi event %x\n", event->event);
	}
	virtscsi_kick_event(vscsi, event_node);
}

static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf)
{
	struct virtio_scsi_event_node *event_node = buf;

	if (!vscsi->stop_events)
		queue_work(system_freezable_wq, &event_node->work);
}

static void virtscsi_event_done(struct virtqueue *vq)
{
	struct Scsi_Host *sh = virtio_scsi_host(vq->vdev);
	struct virtio_scsi *vscsi = shost_priv(sh);

	virtscsi_vq_done(vscsi, &vscsi->event_vq, virtscsi_complete_event);
};

static int __virtscsi_add_cmd(struct virtqueue *vq,
			    struct virtio_scsi_cmd *cmd,
			    size_t req_size, size_t resp_size)
{
	struct scsi_cmnd *sc = cmd->sc;
	struct scatterlist *sgs[6], req, resp;
	struct sg_table *out, *in;
	unsigned out_num = 0, in_num = 0;

	out = in = NULL;

	if (sc && sc->sc_data_direction != DMA_NONE) {
		if (sc->sc_data_direction != DMA_FROM_DEVICE)
			out = &sc->sdb.table;
		if (sc->sc_data_direction != DMA_TO_DEVICE)
			in = &sc->sdb.table;
	}

	/* Request header.  */
	sg_init_one(&req, &cmd->req, req_size);
	sgs[out_num++] = &req;

	/* Data-out buffer.  */
	if (out) {
		/* Place WRITE protection SGLs before Data OUT payload */
		if (scsi_prot_sg_count(sc))
			sgs[out_num++] = scsi_prot_sglist(sc);
		sgs[out_num++] = out->sgl;
	}

	/* Response header.  */
	sg_init_one(&resp, &cmd->resp, resp_size);
	sgs[out_num + in_num++] = &resp;

	/* Data-in buffer */
	if (in) {
		/* Place READ protection SGLs before Data IN payload */
		if (scsi_prot_sg_count(sc))
			sgs[out_num + in_num++] = scsi_prot_sglist(sc);
		sgs[out_num + in_num++] = in->sgl;
	}

	return virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_ATOMIC);
}

static void virtscsi_kick_vq(struct virtio_scsi_vq *vq)
{
	bool needs_kick;
	unsigned long flags;

	spin_lock_irqsave(&vq->vq_lock, flags);
	needs_kick = virtqueue_kick_prepare(vq->vq);
	spin_unlock_irqrestore(&vq->vq_lock, flags);

	if (needs_kick)
		virtqueue_notify(vq->vq);
}

/**
 * virtscsi_add_cmd - add a virtio_scsi_cmd to a virtqueue, optionally kick it
 * @vq		: the struct virtqueue we're talking about
 * @cmd		: command structure
 * @req_size	: size of the request buffer
 * @resp_size	: size of the response buffer
 * @kick	: whether to kick the virtqueue immediately
 */
static int virtscsi_add_cmd(struct virtio_scsi_vq *vq,
			     struct virtio_scsi_cmd *cmd,
			     size_t req_size, size_t resp_size,
			     bool kick)
{
	unsigned long flags;
	int err;
	bool needs_kick = false;

	spin_lock_irqsave(&vq->vq_lock, flags);
	err = __virtscsi_add_cmd(vq->vq, cmd, req_size, resp_size);
	if (!err && kick)
		needs_kick = virtqueue_kick_prepare(vq->vq);

	spin_unlock_irqrestore(&vq->vq_lock, flags);

	if (needs_kick)
		virtqueue_notify(vq->vq);
	return err;
}

static void virtio_scsi_init_hdr(struct virtio_device *vdev,
				 struct virtio_scsi_cmd_req *cmd,
				 struct scsi_cmnd *sc)
{
	cmd->lun[0] = 1;
	cmd->lun[1] = sc->device->id;
	cmd->lun[2] = (sc->device->lun >> 8) | 0x40;
	cmd->lun[3] = sc->device->lun & 0xff;
	cmd->tag = cpu_to_virtio64(vdev, (unsigned long)sc);
	cmd->task_attr = VIRTIO_SCSI_S_SIMPLE;
	cmd->prio = 0;
	cmd->crn = 0;
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
				    struct virtio_scsi_cmd_req_pi *cmd_pi,
				    struct scsi_cmnd *sc)
{
	struct request *rq = scsi_cmd_to_rq(sc);
	struct blk_integrity *bi;

	virtio_scsi_init_hdr(vdev, (struct virtio_scsi_cmd_req *)cmd_pi, sc);

	if (!rq || !scsi_prot_sg_count(sc))
		return;

	bi = blk_get_integrity(rq->q->disk);

	if (sc->sc_data_direction == DMA_TO_DEVICE)
		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
						      bio_integrity_bytes(bi,
							blk_rq_sectors(rq)));
	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
		cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
						     bio_integrity_bytes(bi,
							blk_rq_sectors(rq)));
}
#endif

static struct virtio_scsi_vq *virtscsi_pick_vq_mq(struct virtio_scsi *vscsi,
						  struct scsi_cmnd *sc)
{
	u32 tag = blk_mq_unique_tag(scsi_cmd_to_rq(sc));
	u16 hwq = blk_mq_unique_tag_to_hwq(tag);

	return &vscsi->req_vqs[hwq];
}

static int virtscsi_queuecommand(struct Scsi_Host *shost,
				 struct scsi_cmnd *sc)
{
	struct virtio_scsi *vscsi = shost_priv(shost);
	struct virtio_scsi_vq *req_vq = virtscsi_pick_vq_mq(vscsi, sc);
	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
	bool kick;
	unsigned long flags;
	int req_size;
	int ret;

	BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);

	/* TODO: check feature bit and fail if unsupported?  */
	BUG_ON(sc->sc_data_direction == DMA_BIDIRECTIONAL);

	dev_dbg(&sc->device->sdev_gendev,
		"cmd %p CDB: %#02x\n", sc, sc->cmnd[0]);

	cmd->sc = sc;

	BUG_ON(sc->cmd_len > VIRTIO_SCSI_CDB_SIZE);

#ifdef CONFIG_BLK_DEV_INTEGRITY
	if (virtio_has_feature(vscsi->vdev, VIRTIO_SCSI_F_T10_PI)) {
		virtio_scsi_init_hdr_pi(vscsi->vdev, &cmd->req.cmd_pi, sc);
		memcpy(cmd->req.cmd_pi.cdb, sc->cmnd, sc->cmd_len);
		req_size = sizeof(cmd->req.cmd_pi);
	} else
#endif
	{
		virtio_scsi_init_hdr(vscsi->vdev, &cmd->req.cmd, sc);
		memcpy(cmd->req.cmd.cdb, sc->cmnd, sc->cmd_len);
		req_size = sizeof(cmd->req.cmd);
	}

	kick = (sc->flags & SCMD_LAST) != 0;
	ret = virtscsi_add_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd), kick);
	if (ret == -EIO) {
		cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
		spin_lock_irqsave(&req_vq->vq_lock, flags);
		virtscsi_complete_cmd(vscsi, cmd);
		spin_unlock_irqrestore(&req_vq->vq_lock, flags);
	} else if (ret != 0) {
		return SCSI_MLQUEUE_HOST_BUSY;
	}
	return 0;
}

static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
{
	DECLARE_COMPLETION_ONSTACK(comp);
	int ret = FAILED;

	cmd->comp = &comp;
	if (virtscsi_add_cmd(&vscsi->ctrl_vq, cmd,
			      sizeof cmd->req.tmf, sizeof cmd->resp.tmf, true) < 0)
		goto out;

	wait_for_completion(&comp);
	if (cmd->resp.tmf.response == VIRTIO_SCSI_S_OK ||
	    cmd->resp.tmf.response == VIRTIO_SCSI_S_FUNCTION_SUCCEEDED)
		ret = SUCCESS;

	/*
	 * The spec guarantees that all requests related to the TMF have
	 * been completed, but the callback might not have run yet if
	 * we're using independent interrupts (e.g. MSI).  Poll the
	 * virtqueues once.
	 *
	 * In the abort case, scsi_done() will do nothing, because the
	 * command timed out and hence SCMD_STATE_COMPLETE has been set.
	 */
	virtscsi_poll_requests(vscsi);

out:
	mempool_free(cmd, virtscsi_cmd_pool);
	return ret;
}

static int virtscsi_device_reset(struct scsi_cmnd *sc)
{
	struct virtio_scsi *vscsi = shost_priv(sc->device->host);
	struct virtio_scsi_cmd *cmd;

	sdev_printk(KERN_INFO, sc->device, "device reset\n");
	cmd = mempool_alloc(virtscsi_cmd_pool, GFP_NOIO);
	if (!cmd)
		return FAILED;

	memset(cmd, 0, sizeof(*cmd));
	cmd->req.tmf = (struct virtio_scsi_ctrl_tmf_req){
		.type = VIRTIO_SCSI_T_TMF,
		.subtype = cpu_to_virtio32(vscsi->vdev,
					     VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET),
		.lun[0] = 1,
		.lun[1] = sc->device->id,
		.lun[2] = (sc->device->lun >> 8) | 0x40,
		.lun[3] = sc->device->lun & 0xff,
	};
	return virtscsi_tmf(vscsi, cmd);
}

static int virtscsi_device_alloc(struct scsi_device *sdevice)
{
	/*
	 * Passed through SCSI targets (e.g. with qemu's 'scsi-block')
	 * may have transfer limits which come from the host SCSI
	 * controller or something on the host side other than the
	 * target itself.
	 *
	 * To make this work properly, the hypervisor can adjust the
	 * target's VPD information to advertise these limits.  But
	 * for that to work, the guest has to look at the VPD pages,
	 * which we won't do by default if it is an SPC-2 device, even
	 * if it does actually support it.
	 *
	 * So, set the blist to always try to read the VPD pages.
	 */
	sdevice->sdev_bflags = BLIST_TRY_VPD_PAGES;

	return 0;
}


/**
 * virtscsi_change_queue_depth() - Change a virtscsi target's queue depth
 * @sdev:	Virtscsi target whose queue depth to change
 * @qdepth:	New queue depth
 */
static int virtscsi_change_queue_depth(struct scsi_device *sdev, int qdepth)
{
	struct Scsi_Host *shost = sdev->host;
	int max_depth = shost->cmd_per_lun;

	return scsi_change_queue_depth(sdev, min(max_depth, qdepth));
}

static int virtscsi_abort(struct scsi_cmnd *sc)
{
	struct virtio_scsi *vscsi = shost_priv(sc->device->host);
	struct virtio_scsi_cmd *cmd;

	scmd_printk(KERN_INFO, sc, "abort\n");
	cmd = mempool_alloc(virtscsi_cmd_pool, GFP_NOIO);
	if (!cmd)
		return FAILED;

	memset(cmd, 0, sizeof(*cmd));
	cmd->req.tmf = (struct virtio_scsi_ctrl_tmf_req){
		.type = VIRTIO_SCSI_T_TMF,
		.subtype = VIRTIO_SCSI_T_TMF_ABORT_TASK,
		.lun[0] = 1,
		.lun[1] = sc->device->id,
		.lun[2] = (sc->device->lun >> 8) | 0x40,
		.lun[3] = sc->device->lun & 0xff,
		.tag = cpu_to_virtio64(vscsi->vdev, (unsigned long)sc),
	};
	return virtscsi_tmf(vscsi, cmd);
}

static void virtscsi_map_queues(struct Scsi_Host *shost)
{
	struct virtio_scsi *vscsi = shost_priv(shost);
	int i, qoff;

	for (i = 0, qoff = 0; i < shost->nr_maps; i++) {
		struct blk_mq_queue_map *map = &shost->tag_set.map[i];

		map->nr_queues = vscsi->io_queues[i];
		map->queue_offset = qoff;
		qoff += map->nr_queues;

		if (map->nr_queues == 0)
			continue;

		/*
		 * Regular queues have interrupts and hence CPU affinity is
		 * defined by the core virtio code, but polling queues have
		 * no interrupts so we let the block layer assign CPU affinity.
		 */
		if (i == HCTX_TYPE_POLL)
			blk_mq_map_queues(map);
		else
			blk_mq_virtio_map_queues(map, vscsi->vdev, 2);
	}
}

static int virtscsi_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
{
	struct virtio_scsi *vscsi = shost_priv(shost);
	struct virtio_scsi_vq *virtscsi_vq = &vscsi->req_vqs[queue_num];
	unsigned long flags;
	unsigned int len;
	int found = 0;
	void *buf;

	spin_lock_irqsave(&virtscsi_vq->vq_lock, flags);

	while ((buf = virtqueue_get_buf(virtscsi_vq->vq, &len)) != NULL) {
		virtscsi_complete_cmd(vscsi, buf);
		found++;
	}

	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);

	return found;
}

static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq)
{
	struct virtio_scsi *vscsi = shost_priv(shost);

	virtscsi_kick_vq(&vscsi->req_vqs[hwq]);
}

/*
 * The host guarantees to respond to each command, although I/O
 * latencies might be higher than on bare metal.  Reset the timer
 * unconditionally to give the host a chance to perform EH.
 */
static enum scsi_timeout_action virtscsi_eh_timed_out(struct scsi_cmnd *scmnd)
{
	return SCSI_EH_RESET_TIMER;
}

static const struct scsi_host_template virtscsi_host_template = {
	.module = THIS_MODULE,
	.name = "Virtio SCSI HBA",
	.proc_name = "virtio_scsi",
	.this_id = -1,
	.cmd_size = sizeof(struct virtio_scsi_cmd),
	.queuecommand = virtscsi_queuecommand,
	.mq_poll = virtscsi_mq_poll,
	.commit_rqs = virtscsi_commit_rqs,
	.change_queue_depth = virtscsi_change_queue_depth,
	.eh_abort_handler = virtscsi_abort,
	.eh_device_reset_handler = virtscsi_device_reset,
	.eh_timed_out = virtscsi_eh_timed_out,
	.slave_alloc = virtscsi_device_alloc,

	.dma_boundary = UINT_MAX,
	.map_queues = virtscsi_map_queues,
	.track_queue_depth = 1,
};

#define virtscsi_config_get(vdev, fld) \
	({ \
		__virtio_native_type(struct virtio_scsi_config, fld) __val; \
		virtio_cread(vdev, struct virtio_scsi_config, fld, &__val); \
		__val; \
	})

#define virtscsi_config_set(vdev, fld, val) \
	do { \
		__virtio_native_type(struct virtio_scsi_config, fld) __val = (val); \
		virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \
	} while(0)

static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
			     struct virtqueue *vq)
{
	spin_lock_init(&virtscsi_vq->vq_lock);
	virtscsi_vq->vq = vq;
}

static void virtscsi_remove_vqs(struct virtio_device *vdev)
{
	/* Stop all the virtqueues. */
	virtio_reset_device(vdev);
	vdev->config->del_vqs(vdev);
}

static int virtscsi_init(struct virtio_device *vdev,
			 struct virtio_scsi *vscsi)
{
	int err;
	u32 i;
	u32 num_vqs, num_poll_vqs, num_req_vqs;
	vq_callback_t **callbacks;
	const char **names;
	struct virtqueue **vqs;
	struct irq_affinity desc = { .pre_vectors = 2 };

	num_req_vqs = vscsi->num_queues;
	num_vqs = num_req_vqs + VIRTIO_SCSI_VQ_BASE;
	vqs = kmalloc_array(num_vqs, sizeof(struct virtqueue *), GFP_KERNEL);
	callbacks = kmalloc_array(num_vqs, sizeof(vq_callback_t *),
				  GFP_KERNEL);
	names = kmalloc_array(num_vqs, sizeof(char *), GFP_KERNEL);

	if (!callbacks || !vqs || !names) {
		err = -ENOMEM;
		goto out;
	}

	num_poll_vqs = min_t(unsigned int, virtscsi_poll_queues,
			     num_req_vqs - 1);
	vscsi->io_queues[HCTX_TYPE_DEFAULT] = num_req_vqs - num_poll_vqs;
	vscsi->io_queues[HCTX_TYPE_READ] = 0;
	vscsi->io_queues[HCTX_TYPE_POLL] = num_poll_vqs;

	dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n",
		 vscsi->io_queues[HCTX_TYPE_DEFAULT],
		 vscsi->io_queues[HCTX_TYPE_READ],
		 vscsi->io_queues[HCTX_TYPE_POLL]);

	callbacks[0] = virtscsi_ctrl_done;
	callbacks[1] = virtscsi_event_done;
	names[0] = "control";
	names[1] = "event";
	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs - num_poll_vqs; i++) {
		callbacks[i] = virtscsi_req_done;
		names[i] = "request";
	}

	for (; i < num_vqs; i++) {
		callbacks[i] = NULL;
		names[i] = "request_poll";
	}

	/* Discover virtqueues and write information to configuration.  */
	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
	if (err)
		goto out;

	virtscsi_init_vq(&vscsi->ctrl_vq, vqs[0]);
	virtscsi_init_vq(&vscsi->event_vq, vqs[1]);
	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs; i++)
		virtscsi_init_vq(&vscsi->req_vqs[i - VIRTIO_SCSI_VQ_BASE],
				 vqs[i]);

	virtscsi_config_set(vdev, cdb_size, VIRTIO_SCSI_CDB_SIZE);
	virtscsi_config_set(vdev, sense_size, VIRTIO_SCSI_SENSE_SIZE);

	err = 0;

out:
	kfree(names);
	kfree(callbacks);
	kfree(vqs);
	if (err)
		virtscsi_remove_vqs(vdev);
	return err;
}

static int virtscsi_probe(struct virtio_device *vdev)
{
	struct Scsi_Host *shost;
	struct virtio_scsi *vscsi;
	int err;
	u32 sg_elems, num_targets;
	u32 cmd_per_lun;
	u32 num_queues;

	if (!vdev->config->get) {
		dev_err(&vdev->dev, "%s failure: config access disabled\n",
			__func__);
		return -EINVAL;
	}

	/* We need to know how many queues before we allocate. */
	num_queues = virtscsi_config_get(vdev, num_queues) ? : 1;
	num_queues = min_t(unsigned int, nr_cpu_ids, num_queues);

	num_targets = virtscsi_config_get(vdev, max_target) + 1;

	shost = scsi_host_alloc(&virtscsi_host_template,
				struct_size(vscsi, req_vqs, num_queues));
	if (!shost)
		return -ENOMEM;

	sg_elems = virtscsi_config_get(vdev, seg_max) ?: 1;
	shost->sg_tablesize = sg_elems;
	shost->nr_maps = 1;
	vscsi = shost_priv(shost);
	vscsi->vdev = vdev;
	vscsi->num_queues = num_queues;
	vdev->priv = shost;

	err = virtscsi_init(vdev, vscsi);
	if (err)
		goto virtscsi_init_failed;

	if (vscsi->io_queues[HCTX_TYPE_POLL])
		shost->nr_maps = HCTX_TYPE_POLL + 1;

	shost->can_queue = virtqueue_get_vring_size(vscsi->req_vqs[0].vq);

	cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
	shost->cmd_per_lun = min_t(u32, cmd_per_lun, shost->can_queue);
	shost->max_sectors = virtscsi_config_get(vdev, max_sectors) ?: 0xFFFF;

	/* LUNs > 256 are reported with format 1, so they go in the range
	 * 16640-32767.
	 */
	shost->max_lun = virtscsi_config_get(vdev, max_lun) + 1 + 0x4000;
	shost->max_id = num_targets;
	shost->max_channel = 0;
	shost->max_cmd_len = VIRTIO_SCSI_CDB_SIZE;
	shost->nr_hw_queues = num_queues;

#ifdef CONFIG_BLK_DEV_INTEGRITY
	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_T10_PI)) {
		int host_prot;

		host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION |
			    SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION |
			    SHOST_DIX_TYPE2_PROTECTION | SHOST_DIX_TYPE3_PROTECTION;

		scsi_host_set_prot(shost, host_prot);
		scsi_host_set_guard(shost, SHOST_DIX_GUARD_CRC);
	}
#endif

	err = scsi_add_host(shost, &vdev->dev);
	if (err)
		goto scsi_add_host_failed;

	virtio_device_ready(vdev);

	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
		virtscsi_kick_event_all(vscsi);

	scsi_scan_host(shost);
	return 0;

scsi_add_host_failed:
	vdev->config->del_vqs(vdev);
virtscsi_init_failed:
	scsi_host_put(shost);
	return err;
}

static void virtscsi_remove(struct virtio_device *vdev)
{
	struct Scsi_Host *shost = virtio_scsi_host(vdev);
	struct virtio_scsi *vscsi = shost_priv(shost);

	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
		virtscsi_cancel_event_work(vscsi);

	scsi_remove_host(shost);
	virtscsi_remove_vqs(vdev);
	scsi_host_put(shost);
}

#ifdef CONFIG_PM_SLEEP
static int virtscsi_freeze(struct virtio_device *vdev)
{
	virtscsi_remove_vqs(vdev);
	return 0;
}

static int virtscsi_restore(struct virtio_device *vdev)
{
	struct Scsi_Host *sh = virtio_scsi_host(vdev);
	struct virtio_scsi *vscsi = shost_priv(sh);
	int err;

	err = virtscsi_init(vdev, vscsi);
	if (err)
		return err;

	virtio_device_ready(vdev);

	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
		virtscsi_kick_event_all(vscsi);

	return err;
}
#endif

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_SCSI, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static unsigned int features[] = {
	VIRTIO_SCSI_F_HOTPLUG,
	VIRTIO_SCSI_F_CHANGE,
#ifdef CONFIG_BLK_DEV_INTEGRITY
	VIRTIO_SCSI_F_T10_PI,
#endif
};

static struct virtio_driver virtio_scsi_driver = {
	.feature_table = features,
	.feature_table_size = ARRAY_SIZE(features),
	.driver.name = KBUILD_MODNAME,
	.id_table = id_table,
	.probe = virtscsi_probe,
#ifdef CONFIG_PM_SLEEP
	.freeze = virtscsi_freeze,
	.restore = virtscsi_restore,
#endif
	.remove = virtscsi_remove,
};

static int __init virtio_scsi_init(void)
{
	int ret = -ENOMEM;

	virtscsi_cmd_cache = KMEM_CACHE(virtio_scsi_cmd, 0);
	if (!virtscsi_cmd_cache) {
		pr_err("kmem_cache_create() for virtscsi_cmd_cache failed\n");
		goto error;
	}


	virtscsi_cmd_pool =
		mempool_create_slab_pool(VIRTIO_SCSI_MEMPOOL_SZ,
					 virtscsi_cmd_cache);
	if (!virtscsi_cmd_pool) {
		pr_err("mempool_create() for virtscsi_cmd_pool failed\n");
		goto error;
	}
	ret = register_virtio_driver(&virtio_scsi_driver);
	if (ret < 0)
		goto error;

	return 0;

error:
	mempool_destroy(virtscsi_cmd_pool);
	virtscsi_cmd_pool = NULL;
	kmem_cache_destroy(virtscsi_cmd_cache);
	virtscsi_cmd_cache = NULL;
	return ret;
}

static void __exit virtio_scsi_fini(void)
{
	unregister_virtio_driver(&virtio_scsi_driver);
	mempool_destroy(virtscsi_cmd_pool);
	kmem_cache_destroy(virtscsi_cmd_cache);
}
module_init(virtio_scsi_init);
module_exit(virtio_scsi_fini);

MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio SCSI HBA driver");
MODULE_LICENSE("GPL");