summaryrefslogtreecommitdiffstats
path: root/qemu/hw/block/virtio-blk.c
blob: 1556c9cf5a231b8beb6365d5916da6e34227f8ae (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
/*
 * Virtio Block Device
 *
 * Copyright IBM, Corp. 2007
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "qemu-common.h"
#include "qemu/iov.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "hw/block/block.h"
#include "sysemu/block-backend.h"
#include "sysemu/blockdev.h"
#include "hw/virtio/virtio-blk.h"
#include "dataplane/virtio-blk.h"
#include "migration/migration.h"
#include "block/scsi.h"
#ifdef __linux__
# include <scsi/sg.h>
#endif
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-access.h"

VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
{
    VirtIOBlockReq *req = g_slice_new(VirtIOBlockReq);
    req->dev = s;
    req->qiov.size = 0;
    req->in_len = 0;
    req->next = NULL;
    req->mr_next = NULL;
    return req;
}

void virtio_blk_free_request(VirtIOBlockReq *req)
{
    if (req) {
        g_slice_free(VirtIOBlockReq, req);
    }
}

static void virtio_blk_complete_request(VirtIOBlockReq *req,
                                        unsigned char status)
{
    VirtIOBlock *s = req->dev;
    VirtIODevice *vdev = VIRTIO_DEVICE(s);

    trace_virtio_blk_req_complete(req, status);

    stb_p(&req->in->status, status);
    virtqueue_push(s->vq, &req->elem, req->in_len);
    virtio_notify(vdev, s->vq);
}

static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
{
    req->dev->complete_request(req, status);
}

static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
    bool is_read)
{
    BlockErrorAction action = blk_get_error_action(req->dev->blk,
                                                   is_read, error);
    VirtIOBlock *s = req->dev;

    if (action == BLOCK_ERROR_ACTION_STOP) {
        req->next = s->rq;
        s->rq = req;
    } else if (action == BLOCK_ERROR_ACTION_REPORT) {
        virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
        block_acct_done(blk_get_stats(s->blk), &req->acct);
        virtio_blk_free_request(req);
    }

    blk_error_action(s->blk, action, is_read, error);
    return action != BLOCK_ERROR_ACTION_IGNORE;
}

static void virtio_blk_rw_complete(void *opaque, int ret)
{
    VirtIOBlockReq *next = opaque;

    while (next) {
        VirtIOBlockReq *req = next;
        next = req->mr_next;
        trace_virtio_blk_rw_complete(req, ret);

        if (req->qiov.nalloc != -1) {
            /* If nalloc is != 1 req->qiov is a local copy of the original
             * external iovec. It was allocated in submit_merged_requests
             * to be able to merge requests. */
            qemu_iovec_destroy(&req->qiov);
        }

        if (ret) {
            int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
            bool is_read = !(p & VIRTIO_BLK_T_OUT);
            /* Note that memory may be dirtied on read failure.  If the
             * virtio request is not completed here, as is the case for
             * BLOCK_ERROR_ACTION_STOP, the memory may not be copied
             * correctly during live migration.  While this is ugly,
             * it is acceptable because the device is free to write to
             * the memory until the request is completed (which will
             * happen on the other side of the migration).
             */
            if (virtio_blk_handle_rw_error(req, -ret, is_read)) {
                continue;
            }
        }

        virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
        block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
        virtio_blk_free_request(req);
    }
}

static void virtio_blk_flush_complete(void *opaque, int ret)
{
    VirtIOBlockReq *req = opaque;

    if (ret) {
        if (virtio_blk_handle_rw_error(req, -ret, 0)) {
            return;
        }
    }

    virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
    block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
    virtio_blk_free_request(req);
}

#ifdef __linux__

typedef struct {
    VirtIOBlockReq *req;
    struct sg_io_hdr hdr;
} VirtIOBlockIoctlReq;

static void virtio_blk_ioctl_complete(void *opaque, int status)
{
    VirtIOBlockIoctlReq *ioctl_req = opaque;
    VirtIOBlockReq *req = ioctl_req->req;
    VirtIODevice *vdev = VIRTIO_DEVICE(req->dev);
    struct virtio_scsi_inhdr *scsi;
    struct sg_io_hdr *hdr;

    scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;

    if (status) {
        status = VIRTIO_BLK_S_UNSUPP;
        virtio_stl_p(vdev, &scsi->errors, 255);
        goto out;
    }

    hdr = &ioctl_req->hdr;
    /*
     * From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi)
     * clear the masked_status field [hence status gets cleared too, see
     * block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED
     * status has occurred.  However they do set DRIVER_SENSE in driver_status
     * field. Also a (sb_len_wr > 0) indicates there is a sense buffer.
     */
    if (hdr->status == 0 && hdr->sb_len_wr > 0) {
        hdr->status = CHECK_CONDITION;
    }

    virtio_stl_p(vdev, &scsi->errors,
                 hdr->status | (hdr->msg_status << 8) |
                 (hdr->host_status << 16) | (hdr->driver_status << 24));
    virtio_stl_p(vdev, &scsi->residual, hdr->resid);
    virtio_stl_p(vdev, &scsi->sense_len, hdr->sb_len_wr);
    virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len);

out:
    virtio_blk_req_complete(req, status);
    virtio_blk_free_request(req);
    g_free(ioctl_req);
}

#endif

static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s)
{
    VirtIOBlockReq *req = virtio_blk_alloc_request(s);

    if (!virtqueue_pop(s->vq, &req->elem)) {
        virtio_blk_free_request(req);
        return NULL;
    }

    return req;
}

static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req)
{
    int status = VIRTIO_BLK_S_OK;
    struct virtio_scsi_inhdr *scsi = NULL;
    VirtIODevice *vdev = VIRTIO_DEVICE(req->dev);
    VirtQueueElement *elem = &req->elem;
    VirtIOBlock *blk = req->dev;

#ifdef __linux__
    int i;
    VirtIOBlockIoctlReq *ioctl_req;
    BlockAIOCB *acb;
#endif

    /*
     * We require at least one output segment each for the virtio_blk_outhdr
     * and the SCSI command block.
     *
     * We also at least require the virtio_blk_inhdr, the virtio_scsi_inhdr
     * and the sense buffer pointer in the input segments.
     */
    if (elem->out_num < 2 || elem->in_num < 3) {
        status = VIRTIO_BLK_S_IOERR;
        goto fail;
    }

    /*
     * The scsi inhdr is placed in the second-to-last input segment, just
     * before the regular inhdr.
     */
    scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base;

    if (!blk->conf.scsi) {
        status = VIRTIO_BLK_S_UNSUPP;
        goto fail;
    }

    /*
     * No support for bidirection commands yet.
     */
    if (elem->out_num > 2 && elem->in_num > 3) {
        status = VIRTIO_BLK_S_UNSUPP;
        goto fail;
    }

#ifdef __linux__
    ioctl_req = g_new0(VirtIOBlockIoctlReq, 1);
    ioctl_req->req = req;
    ioctl_req->hdr.interface_id = 'S';
    ioctl_req->hdr.cmd_len = elem->out_sg[1].iov_len;
    ioctl_req->hdr.cmdp = elem->out_sg[1].iov_base;
    ioctl_req->hdr.dxfer_len = 0;

    if (elem->out_num > 2) {
        /*
         * If there are more than the minimally required 2 output segments
         * there is write payload starting from the third iovec.
         */
        ioctl_req->hdr.dxfer_direction = SG_DXFER_TO_DEV;
        ioctl_req->hdr.iovec_count = elem->out_num - 2;

        for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
            ioctl_req->hdr.dxfer_len += elem->out_sg[i + 2].iov_len;
        }

        ioctl_req->hdr.dxferp = elem->out_sg + 2;

    } else if (elem->in_num > 3) {
        /*
         * If we have more than 3 input segments the guest wants to actually
         * read data.
         */
        ioctl_req->hdr.dxfer_direction = SG_DXFER_FROM_DEV;
        ioctl_req->hdr.iovec_count = elem->in_num - 3;
        for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
            ioctl_req->hdr.dxfer_len += elem->in_sg[i].iov_len;
        }

        ioctl_req->hdr.dxferp = elem->in_sg;
    } else {
        /*
         * Some SCSI commands don't actually transfer any data.
         */
        ioctl_req->hdr.dxfer_direction = SG_DXFER_NONE;
    }

    ioctl_req->hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base;
    ioctl_req->hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len;

    acb = blk_aio_ioctl(blk->blk, SG_IO, &ioctl_req->hdr,
                        virtio_blk_ioctl_complete, ioctl_req);
    if (!acb) {
        g_free(ioctl_req);
        status = VIRTIO_BLK_S_UNSUPP;
        goto fail;
    }
    return -EINPROGRESS;
#else
    abort();
#endif

fail:
    /* Just put anything nonzero so that the ioctl fails in the guest.  */
    if (scsi) {
        virtio_stl_p(vdev, &scsi->errors, 255);
    }
    return status;
}

static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
{
    int status;

    status = virtio_blk_handle_scsi_req(req);
    if (status != -EINPROGRESS) {
        virtio_blk_req_complete(req, status);
        virtio_blk_free_request(req);
    }
}

static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
                                   int start, int num_reqs, int niov)
{
    QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
    int64_t sector_num = mrb->reqs[start]->sector_num;
    int nb_sectors = mrb->reqs[start]->qiov.size / BDRV_SECTOR_SIZE;
    bool is_write = mrb->is_write;

    if (num_reqs > 1) {
        int i;
        struct iovec *tmp_iov = qiov->iov;
        int tmp_niov = qiov->niov;

        /* mrb->reqs[start]->qiov was initialized from external so we can't
         * modifiy it here. We need to initialize it locally and then add the
         * external iovecs. */
        qemu_iovec_init(qiov, niov);

        for (i = 0; i < tmp_niov; i++) {
            qemu_iovec_add(qiov, tmp_iov[i].iov_base, tmp_iov[i].iov_len);
        }

        for (i = start + 1; i < start + num_reqs; i++) {
            qemu_iovec_concat(qiov, &mrb->reqs[i]->qiov, 0,
                              mrb->reqs[i]->qiov.size);
            mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
            nb_sectors += mrb->reqs[i]->qiov.size / BDRV_SECTOR_SIZE;
        }
        assert(nb_sectors == qiov->size / BDRV_SECTOR_SIZE);

        trace_virtio_blk_submit_multireq(mrb, start, num_reqs, sector_num,
                                         nb_sectors, is_write);
        block_acct_merge_done(blk_get_stats(blk),
                              is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ,
                              num_reqs - 1);
    }

    if (is_write) {
        blk_aio_writev(blk, sector_num, qiov, nb_sectors,
                       virtio_blk_rw_complete, mrb->reqs[start]);
    } else {
        blk_aio_readv(blk, sector_num, qiov, nb_sectors,
                      virtio_blk_rw_complete, mrb->reqs[start]);
    }
}

static int multireq_compare(const void *a, const void *b)
{
    const VirtIOBlockReq *req1 = *(VirtIOBlockReq **)a,
                         *req2 = *(VirtIOBlockReq **)b;

    /*
     * Note that we can't simply subtract sector_num1 from sector_num2
     * here as that could overflow the return value.
     */
    if (req1->sector_num > req2->sector_num) {
        return 1;
    } else if (req1->sector_num < req2->sector_num) {
        return -1;
    } else {
        return 0;
    }
}

void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
{
    int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0;
    int max_xfer_len = 0;
    int64_t sector_num = 0;

    if (mrb->num_reqs == 1) {
        submit_requests(blk, mrb, 0, 1, -1);
        mrb->num_reqs = 0;
        return;
    }

    max_xfer_len = blk_get_max_transfer_length(mrb->reqs[0]->dev->blk);
    max_xfer_len = MIN_NON_ZERO(max_xfer_len, BDRV_REQUEST_MAX_SECTORS);

    qsort(mrb->reqs, mrb->num_reqs, sizeof(*mrb->reqs),
          &multireq_compare);

    for (i = 0; i < mrb->num_reqs; i++) {
        VirtIOBlockReq *req = mrb->reqs[i];
        if (num_reqs > 0) {
            bool merge = true;

            /* merge would exceed maximum number of IOVs */
            if (niov + req->qiov.niov > IOV_MAX) {
                merge = false;
            }

            /* merge would exceed maximum transfer length of backend device */
            if (req->qiov.size / BDRV_SECTOR_SIZE + nb_sectors > max_xfer_len) {
                merge = false;
            }

            /* requests are not sequential */
            if (sector_num + nb_sectors != req->sector_num) {
                merge = false;
            }

            if (!merge) {
                submit_requests(blk, mrb, start, num_reqs, niov);
                num_reqs = 0;
            }
        }

        if (num_reqs == 0) {
            sector_num = req->sector_num;
            nb_sectors = niov = 0;
            start = i;
        }

        nb_sectors += req->qiov.size / BDRV_SECTOR_SIZE;
        niov += req->qiov.niov;
        num_reqs++;
    }

    submit_requests(blk, mrb, start, num_reqs, niov);
    mrb->num_reqs = 0;
}

static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
    block_acct_start(blk_get_stats(req->dev->blk), &req->acct, 0,
                     BLOCK_ACCT_FLUSH);

    /*
     * Make sure all outstanding writes are posted to the backing device.
     */
    if (mrb->is_write && mrb->num_reqs > 0) {
        virtio_blk_submit_multireq(req->dev->blk, mrb);
    }
    blk_aio_flush(req->dev->blk, virtio_blk_flush_complete, req);
}

static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
                                     uint64_t sector, size_t size)
{
    uint64_t nb_sectors = size >> BDRV_SECTOR_BITS;
    uint64_t total_sectors;

    if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
        return false;
    }
    if (sector & dev->sector_mask) {
        return false;
    }
    if (size % dev->conf.conf.logical_block_size) {
        return false;
    }
    blk_get_geometry(dev->blk, &total_sectors);
    if (sector > total_sectors || nb_sectors > total_sectors - sector) {
        return false;
    }
    return true;
}

void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
    uint32_t type;
    struct iovec *in_iov = req->elem.in_sg;
    struct iovec *iov = req->elem.out_sg;
    unsigned in_num = req->elem.in_num;
    unsigned out_num = req->elem.out_num;

    if (req->elem.out_num < 1 || req->elem.in_num < 1) {
        error_report("virtio-blk missing headers");
        exit(1);
    }

    if (unlikely(iov_to_buf(iov, out_num, 0, &req->out,
                            sizeof(req->out)) != sizeof(req->out))) {
        error_report("virtio-blk request outhdr too short");
        exit(1);
    }

    iov_discard_front(&iov, &out_num, sizeof(req->out));

    if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
        error_report("virtio-blk request inhdr too short");
        exit(1);
    }

    /* We always touch the last byte, so just see how big in_iov is.  */
    req->in_len = iov_size(in_iov, in_num);
    req->in = (void *)in_iov[in_num - 1].iov_base
              + in_iov[in_num - 1].iov_len
              - sizeof(struct virtio_blk_inhdr);
    iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));

    type = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);

    /* VIRTIO_BLK_T_OUT defines the command direction. VIRTIO_BLK_T_BARRIER
     * is an optional flag. Although a guest should not send this flag if
     * not negotiated we ignored it in the past. So keep ignoring it. */
    switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
    case VIRTIO_BLK_T_IN:
    {
        bool is_write = type & VIRTIO_BLK_T_OUT;
        req->sector_num = virtio_ldq_p(VIRTIO_DEVICE(req->dev),
                                       &req->out.sector);

        if (is_write) {
            qemu_iovec_init_external(&req->qiov, iov, out_num);
            trace_virtio_blk_handle_write(req, req->sector_num,
                                          req->qiov.size / BDRV_SECTOR_SIZE);
        } else {
            qemu_iovec_init_external(&req->qiov, in_iov, in_num);
            trace_virtio_blk_handle_read(req, req->sector_num,
                                         req->qiov.size / BDRV_SECTOR_SIZE);
        }

        if (!virtio_blk_sect_range_ok(req->dev, req->sector_num,
                                      req->qiov.size)) {
            virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
            virtio_blk_free_request(req);
            return;
        }

        block_acct_start(blk_get_stats(req->dev->blk),
                         &req->acct, req->qiov.size,
                         is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);

        /* merge would exceed maximum number of requests or IO direction
         * changes */
        if (mrb->num_reqs > 0 && (mrb->num_reqs == VIRTIO_BLK_MAX_MERGE_REQS ||
                                  is_write != mrb->is_write ||
                                  !req->dev->conf.request_merging)) {
            virtio_blk_submit_multireq(req->dev->blk, mrb);
        }

        assert(mrb->num_reqs < VIRTIO_BLK_MAX_MERGE_REQS);
        mrb->reqs[mrb->num_reqs++] = req;
        mrb->is_write = is_write;
        break;
    }
    case VIRTIO_BLK_T_FLUSH:
        virtio_blk_handle_flush(req, mrb);
        break;
    case VIRTIO_BLK_T_SCSI_CMD:
        virtio_blk_handle_scsi(req);
        break;
    case VIRTIO_BLK_T_GET_ID:
    {
        VirtIOBlock *s = req->dev;

        /*
         * NB: per existing s/n string convention the string is
         * terminated by '\0' only when shorter than buffer.
         */
        const char *serial = s->conf.serial ? s->conf.serial : "";
        size_t size = MIN(strlen(serial) + 1,
                          MIN(iov_size(in_iov, in_num),
                              VIRTIO_BLK_ID_BYTES));
        iov_from_buf(in_iov, in_num, 0, serial, size);
        virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
        virtio_blk_free_request(req);
        break;
    }
    default:
        virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
        virtio_blk_free_request(req);
    }
}

static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);
    VirtIOBlockReq *req;
    MultiReqBuffer mrb = {};

    /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
     * dataplane here instead of waiting for .set_status().
     */
    if (s->dataplane) {
        virtio_blk_data_plane_start(s->dataplane);
        return;
    }

    while ((req = virtio_blk_get_request(s))) {
        virtio_blk_handle_request(req, &mrb);
    }

    if (mrb.num_reqs) {
        virtio_blk_submit_multireq(s->blk, &mrb);
    }
}

static void virtio_blk_dma_restart_bh(void *opaque)
{
    VirtIOBlock *s = opaque;
    VirtIOBlockReq *req = s->rq;
    MultiReqBuffer mrb = {};

    qemu_bh_delete(s->bh);
    s->bh = NULL;

    s->rq = NULL;

    while (req) {
        VirtIOBlockReq *next = req->next;
        virtio_blk_handle_request(req, &mrb);
        req = next;
    }

    if (mrb.num_reqs) {
        virtio_blk_submit_multireq(s->blk, &mrb);
    }
}

static void virtio_blk_dma_restart_cb(void *opaque, int running,
                                      RunState state)
{
    VirtIOBlock *s = opaque;

    if (!running) {
        return;
    }

    if (!s->bh) {
        s->bh = aio_bh_new(blk_get_aio_context(s->conf.conf.blk),
                           virtio_blk_dma_restart_bh, s);
        qemu_bh_schedule(s->bh);
    }
}

static void virtio_blk_reset(VirtIODevice *vdev)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);
    AioContext *ctx;

    /*
     * This should cancel pending requests, but can't do nicely until there
     * are per-device request lists.
     */
    ctx = blk_get_aio_context(s->blk);
    aio_context_acquire(ctx);
    blk_drain(s->blk);

    if (s->dataplane) {
        virtio_blk_data_plane_stop(s->dataplane);
    }
    aio_context_release(ctx);

    blk_set_enable_write_cache(s->blk, s->original_wce);
}

/* coalesce internal state, copy to pci i/o region 0
 */
static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);
    BlockConf *conf = &s->conf.conf;
    struct virtio_blk_config blkcfg;
    uint64_t capacity;
    int blk_size = conf->logical_block_size;

    blk_get_geometry(s->blk, &capacity);
    memset(&blkcfg, 0, sizeof(blkcfg));
    virtio_stq_p(vdev, &blkcfg.capacity, capacity);
    virtio_stl_p(vdev, &blkcfg.seg_max, 128 - 2);
    virtio_stw_p(vdev, &blkcfg.geometry.cylinders, conf->cyls);
    virtio_stl_p(vdev, &blkcfg.blk_size, blk_size);
    virtio_stw_p(vdev, &blkcfg.min_io_size, conf->min_io_size / blk_size);
    virtio_stw_p(vdev, &blkcfg.opt_io_size, conf->opt_io_size / blk_size);
    blkcfg.geometry.heads = conf->heads;
    /*
     * We must ensure that the block device capacity is a multiple of
     * the logical block size. If that is not the case, let's use
     * sector_mask to adopt the geometry to have a correct picture.
     * For those devices where the capacity is ok for the given geometry
     * we don't touch the sector value of the geometry, since some devices
     * (like s390 dasd) need a specific value. Here the capacity is already
     * cyls*heads*secs*blk_size and the sector value is not block size
     * divided by 512 - instead it is the amount of blk_size blocks
     * per track (cylinder).
     */
    if (blk_getlength(s->blk) /  conf->heads / conf->secs % blk_size) {
        blkcfg.geometry.sectors = conf->secs & ~s->sector_mask;
    } else {
        blkcfg.geometry.sectors = conf->secs;
    }
    blkcfg.size_max = 0;
    blkcfg.physical_block_exp = get_physical_block_exp(conf);
    blkcfg.alignment_offset = 0;
    blkcfg.wce = blk_enable_write_cache(s->blk);
    memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
}

static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);
    struct virtio_blk_config blkcfg;

    memcpy(&blkcfg, config, sizeof(blkcfg));

    aio_context_acquire(blk_get_aio_context(s->blk));
    blk_set_enable_write_cache(s->blk, blkcfg.wce != 0);
    aio_context_release(blk_get_aio_context(s->blk));
}

static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
                                        Error **errp)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);

    virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX);
    virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
    virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
    virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
    if (__virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
        if (s->conf.scsi) {
            error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
            return 0;
        }
    } else {
        virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT);
        virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
    }

    if (s->conf.config_wce) {
        virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE);
    }
    if (blk_enable_write_cache(s->blk)) {
        virtio_add_feature(&features, VIRTIO_BLK_F_WCE);
    }
    if (blk_is_read_only(s->blk)) {
        virtio_add_feature(&features, VIRTIO_BLK_F_RO);
    }

    return features;
}

static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);

    if (s->dataplane && !(status & (VIRTIO_CONFIG_S_DRIVER |
                                    VIRTIO_CONFIG_S_DRIVER_OK))) {
        virtio_blk_data_plane_stop(s->dataplane);
    }

    if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
        return;
    }

    /* A guest that supports VIRTIO_BLK_F_CONFIG_WCE must be able to send
     * cache flushes.  Thus, the "auto writethrough" behavior is never
     * necessary for guests that support the VIRTIO_BLK_F_CONFIG_WCE feature.
     * Leaving it enabled would break the following sequence:
     *
     *     Guest started with "-drive cache=writethrough"
     *     Guest sets status to 0
     *     Guest sets DRIVER bit in status field
     *     Guest reads host features (WCE=0, CONFIG_WCE=1)
     *     Guest writes guest features (WCE=0, CONFIG_WCE=1)
     *     Guest writes 1 to the WCE configuration field (writeback mode)
     *     Guest sets DRIVER_OK bit in status field
     *
     * s->blk would erroneously be placed in writethrough mode.
     */
    if (!virtio_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE)) {
        aio_context_acquire(blk_get_aio_context(s->blk));
        blk_set_enable_write_cache(s->blk,
                                   virtio_has_feature(vdev, VIRTIO_BLK_F_WCE));
        aio_context_release(blk_get_aio_context(s->blk));
    }
}

static void virtio_blk_save(QEMUFile *f, void *opaque)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(opaque);

    virtio_save(vdev, f);
}
    
static void virtio_blk_save_device(VirtIODevice *vdev, QEMUFile *f)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);
    VirtIOBlockReq *req = s->rq;

    while (req) {
        qemu_put_sbyte(f, 1);
        qemu_put_buffer(f, (unsigned char *)&req->elem,
                        sizeof(VirtQueueElement));
        req = req->next;
    }
    qemu_put_sbyte(f, 0);
}

static int virtio_blk_load(QEMUFile *f, void *opaque, int version_id)
{
    VirtIOBlock *s = opaque;
    VirtIODevice *vdev = VIRTIO_DEVICE(s);

    if (version_id != 2)
        return -EINVAL;

    return virtio_load(vdev, f, version_id);
}

static int virtio_blk_load_device(VirtIODevice *vdev, QEMUFile *f,
                                  int version_id)
{
    VirtIOBlock *s = VIRTIO_BLK(vdev);

    while (qemu_get_sbyte(f)) {
        VirtIOBlockReq *req = virtio_blk_alloc_request(s);
        qemu_get_buffer(f, (unsigned char *)&req->elem,
                        sizeof(VirtQueueElement));
        req->next = s->rq;
        s->rq = req;

        virtqueue_map_sg(req->elem.in_sg, req->elem.in_addr,
            req->elem.in_num, 1);
        virtqueue_map_sg(req->elem.out_sg, req->elem.out_addr,
            req->elem.out_num, 0);
    }

    return 0;
}

static void virtio_blk_resize(void *opaque)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(opaque);

    virtio_notify_config(vdev);
}

static const BlockDevOps virtio_block_ops = {
    .resize_cb = virtio_blk_resize,
};

/* Disable dataplane thread during live migration since it does not
 * update the dirty memory bitmap yet.
 */
static void virtio_blk_migration_state_changed(Notifier *notifier, void *data)
{
    VirtIOBlock *s = container_of(notifier, VirtIOBlock,
                                  migration_state_notifier);
    MigrationState *mig = data;
    Error *err = NULL;

    if (migration_in_setup(mig)) {
        if (!s->dataplane) {
            return;
        }
        virtio_blk_data_plane_destroy(s->dataplane);
        s->dataplane = NULL;
    } else if (migration_has_finished(mig) ||
               migration_has_failed(mig)) {
        if (s->dataplane) {
            return;
        }
        blk_drain_all(); /* complete in-flight non-dataplane requests */
        virtio_blk_data_plane_create(VIRTIO_DEVICE(s), &s->conf,
                                     &s->dataplane, &err);
        if (err != NULL) {
            error_report_err(err);
        }
    }
}

static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VirtIOBlock *s = VIRTIO_BLK(dev);
    VirtIOBlkConf *conf = &s->conf;
    Error *err = NULL;
    static int virtio_blk_id;

    if (!conf->conf.blk) {
        error_setg(errp, "drive property not set");
        return;
    }
    if (!blk_is_inserted(conf->conf.blk)) {
        error_setg(errp, "Device needs media, but drive is empty");
        return;
    }

    blkconf_serial(&conf->conf, &conf->serial);
    s->original_wce = blk_enable_write_cache(conf->conf.blk);
    blkconf_geometry(&conf->conf, NULL, 65535, 255, 255, &err);
    if (err) {
        error_propagate(errp, err);
        return;
    }
    blkconf_blocksizes(&conf->conf);

    virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK,
                sizeof(struct virtio_blk_config));

    s->blk = conf->conf.blk;
    s->rq = NULL;
    s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;

    s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output);
    s->complete_request = virtio_blk_complete_request;
    virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
    if (err != NULL) {
        error_propagate(errp, err);
        virtio_cleanup(vdev);
        return;
    }
    s->migration_state_notifier.notify = virtio_blk_migration_state_changed;
    add_migration_state_change_notifier(&s->migration_state_notifier);

    s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
    register_savevm(dev, "virtio-blk", virtio_blk_id++, 2,
                    virtio_blk_save, virtio_blk_load, s);
    blk_set_dev_ops(s->blk, &virtio_block_ops, s);
    blk_set_guest_block_size(s->blk, s->conf.conf.logical_block_size);

    blk_iostatus_enable(s->blk);
}

static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
    VirtIOBlock *s = VIRTIO_BLK(dev);

    remove_migration_state_change_notifier(&s->migration_state_notifier);
    virtio_blk_data_plane_destroy(s->dataplane);
    s->dataplane = NULL;
    qemu_del_vm_change_state_handler(s->change);
    unregister_savevm(dev, "virtio-blk", s);
    blockdev_mark_auto_del(s->blk);
    virtio_cleanup(vdev);
}

static void virtio_blk_instance_init(Object *obj)
{
    VirtIOBlock *s = VIRTIO_BLK(obj);

    object_property_add_link(obj, "iothread", TYPE_IOTHREAD,
                             (Object **)&s->conf.iothread,
                             qdev_prop_allow_set_link_before_realize,
                             OBJ_PROP_LINK_UNREF_ON_RELEASE, NULL);
    device_add_bootindex_property(obj, &s->conf.conf.bootindex,
                                  "bootindex", "/disk@0,0",
                                  DEVICE(obj), NULL);
}

static Property virtio_blk_properties[] = {
    DEFINE_BLOCK_PROPERTIES(VirtIOBlock, conf.conf),
    DEFINE_BLOCK_CHS_PROPERTIES(VirtIOBlock, conf.conf),
    DEFINE_PROP_STRING("serial", VirtIOBlock, conf.serial),
    DEFINE_PROP_BIT("config-wce", VirtIOBlock, conf.config_wce, 0, true),
#ifdef __linux__
    DEFINE_PROP_BIT("scsi", VirtIOBlock, conf.scsi, 0, true),
#endif
    DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0,
                    true),
    DEFINE_PROP_BIT("x-data-plane", VirtIOBlock, conf.data_plane, 0, false),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_blk_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);

    dc->props = virtio_blk_properties;
    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
    vdc->realize = virtio_blk_device_realize;
    vdc->unrealize = virtio_blk_device_unrealize;
    vdc->get_config = virtio_blk_update_config;
    vdc->set_config = virtio_blk_set_config;
    vdc->get_features = virtio_blk_get_features;
    vdc->set_status = virtio_blk_set_status;
    vdc->reset = virtio_blk_reset;
    vdc->save = virtio_blk_save_device;
    vdc->load = virtio_blk_load_device;
}

static const TypeInfo virtio_device_info = {
    .name = TYPE_VIRTIO_BLK,
    .parent = TYPE_VIRTIO_DEVICE,
    .instance_size = sizeof(VirtIOBlock),
    .instance_init = virtio_blk_instance_init,
    .class_init = virtio_blk_class_init,
};

static void virtio_register_types(void)
{
    type_register_static(&virtio_device_info);
}

type_init(virtio_register_types)