aboutsummaryrefslogtreecommitdiff
path: root/hw/virtio.c
blob: 0455a9e8f3f1fe7d09335f008617d10faf91ad38 (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
/*
 * Virtio Support
 *
 * 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 <inttypes.h>

#include "trace.h"
#include "qemu/error-report.h"
#include "virtio.h"
#include "qemu/atomic.h"

/* The alignment to use between consumer and producer parts of vring.
 * x86 pagesize again. */
#define VIRTIO_PCI_VRING_ALIGN         4096

typedef struct VRingDesc
{
    uint64_t addr;
    uint32_t len;
    uint16_t flags;
    uint16_t next;
} VRingDesc;

typedef struct VRingAvail
{
    uint16_t flags;
    uint16_t idx;
    uint16_t ring[0];
} VRingAvail;

typedef struct VRingUsedElem
{
    uint32_t id;
    uint32_t len;
} VRingUsedElem;

typedef struct VRingUsed
{
    uint16_t flags;
    uint16_t idx;
    VRingUsedElem ring[0];
} VRingUsed;

typedef struct VRing
{
    unsigned int num;
    hwaddr desc;
    hwaddr avail;
    hwaddr used;
} VRing;

struct VirtQueue
{
    VRing vring;
    hwaddr pa;
    uint16_t last_avail_idx;
    /* Last used index value we have signalled on */
    uint16_t signalled_used;

    /* Last used index value we have signalled on */
    bool signalled_used_valid;

    /* Notification enabled? */
    bool notification;

    int inuse;

    uint16_t vector;
    void (*handle_output)(VirtIODevice *vdev, VirtQueue *vq);
    VirtIODevice *vdev;
    EventNotifier guest_notifier;
    EventNotifier host_notifier;
};

/* virt queue functions */
static void virtqueue_init(VirtQueue *vq)
{
    hwaddr pa = vq->pa;

    vq->vring.desc = pa;
    vq->vring.avail = pa + vq->vring.num * sizeof(VRingDesc);
    vq->vring.used = vring_align(vq->vring.avail +
                                 offsetof(VRingAvail, ring[vq->vring.num]),
                                 VIRTIO_PCI_VRING_ALIGN);
}

static inline uint64_t vring_desc_addr(hwaddr desc_pa, int i)
{
    hwaddr pa;
    pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, addr);
    return ldq_phys(pa);
}

static inline uint32_t vring_desc_len(hwaddr desc_pa, int i)
{
    hwaddr pa;
    pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, len);
    return ldl_phys(pa);
}

static inline uint16_t vring_desc_flags(hwaddr desc_pa, int i)
{
    hwaddr pa;
    pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, flags);
    return lduw_phys(pa);
}

static inline uint16_t vring_desc_next(hwaddr desc_pa, int i)
{
    hwaddr pa;
    pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, next);
    return lduw_phys(pa);
}

static inline uint16_t vring_avail_flags(VirtQueue *vq)
{
    hwaddr pa;
    pa = vq->vring.avail + offsetof(VRingAvail, flags);
    return lduw_phys(pa);
}

static inline uint16_t vring_avail_idx(VirtQueue *vq)
{
    hwaddr pa;
    pa = vq->vring.avail + offsetof(VRingAvail, idx);
    return lduw_phys(pa);
}

static inline uint16_t vring_avail_ring(VirtQueue *vq, int i)
{
    hwaddr pa;
    pa = vq->vring.avail + offsetof(VRingAvail, ring[i]);
    return lduw_phys(pa);
}

static inline uint16_t vring_used_event(VirtQueue *vq)
{
    return vring_avail_ring(vq, vq->vring.num);
}

static inline void vring_used_ring_id(VirtQueue *vq, int i, uint32_t val)
{
    hwaddr pa;
    pa = vq->vring.used + offsetof(VRingUsed, ring[i].id);
    stl_phys(pa, val);
}

static inline void vring_used_ring_len(VirtQueue *vq, int i, uint32_t val)
{
    hwaddr pa;
    pa = vq->vring.used + offsetof(VRingUsed, ring[i].len);
    stl_phys(pa, val);
}

static uint16_t vring_used_idx(VirtQueue *vq)
{
    hwaddr pa;
    pa = vq->vring.used + offsetof(VRingUsed, idx);
    return lduw_phys(pa);
}

static inline void vring_used_idx_set(VirtQueue *vq, uint16_t val)
{
    hwaddr pa;
    pa = vq->vring.used + offsetof(VRingUsed, idx);
    stw_phys(pa, val);
}

static inline void vring_used_flags_set_bit(VirtQueue *vq, int mask)
{
    hwaddr pa;
    pa = vq->vring.used + offsetof(VRingUsed, flags);
    stw_phys(pa, lduw_phys(pa) | mask);
}

static inline void vring_used_flags_unset_bit(VirtQueue *vq, int mask)
{
    hwaddr pa;
    pa = vq->vring.used + offsetof(VRingUsed, flags);
    stw_phys(pa, lduw_phys(pa) & ~mask);
}

static inline void vring_avail_event(VirtQueue *vq, uint16_t val)
{
    hwaddr pa;
    if (!vq->notification) {
        return;
    }
    pa = vq->vring.used + offsetof(VRingUsed, ring[vq->vring.num]);
    stw_phys(pa, val);
}

void virtio_queue_set_notification(VirtQueue *vq, int enable)
{
    vq->notification = enable;
    if (vq->vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
        vring_avail_event(vq, vring_avail_idx(vq));
    } else if (enable) {
        vring_used_flags_unset_bit(vq, VRING_USED_F_NO_NOTIFY);
    } else {
        vring_used_flags_set_bit(vq, VRING_USED_F_NO_NOTIFY);
    }
    if (enable) {
        /* Expose avail event/used flags before caller checks the avail idx. */
        smp_mb();
    }
}

int virtio_queue_ready(VirtQueue *vq)
{
    return vq->vring.avail != 0;
}

int virtio_queue_empty(VirtQueue *vq)
{
    return vring_avail_idx(vq) == vq->last_avail_idx;
}

void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
                    unsigned int len, unsigned int idx)
{
    unsigned int offset;
    int i;

    trace_virtqueue_fill(vq, elem, len, idx);

    offset = 0;
    for (i = 0; i < elem->in_num; i++) {
        size_t size = MIN(len - offset, elem->in_sg[i].iov_len);

        cpu_physical_memory_unmap(elem->in_sg[i].iov_base,
                                  elem->in_sg[i].iov_len,
                                  1, size);

        offset += size;
    }

    for (i = 0; i < elem->out_num; i++)
        cpu_physical_memory_unmap(elem->out_sg[i].iov_base,
                                  elem->out_sg[i].iov_len,
                                  0, elem->out_sg[i].iov_len);

    idx = (idx + vring_used_idx(vq)) % vq->vring.num;

    /* Get a pointer to the next entry in the used ring. */
    vring_used_ring_id(vq, idx, elem->index);
    vring_used_ring_len(vq, idx, len);
}

void virtqueue_flush(VirtQueue *vq, unsigned int count)
{
    uint16_t old, new;
    /* Make sure buffer is written before we update index. */
    smp_wmb();
    trace_virtqueue_flush(vq, count);
    old = vring_used_idx(vq);
    new = old + count;
    vring_used_idx_set(vq, new);
    vq->inuse -= count;
    if (unlikely((int16_t)(new - vq->signalled_used) < (uint16_t)(new - old)))
        vq->signalled_used_valid = false;
}

void virtqueue_push(VirtQueue *vq, const VirtQueueElement *elem,
                    unsigned int len)
{
    virtqueue_fill(vq, elem, len, 0);
    virtqueue_flush(vq, 1);
}

static int virtqueue_num_heads(VirtQueue *vq, unsigned int idx)
{
    uint16_t num_heads = vring_avail_idx(vq) - idx;

    /* Check it isn't doing very strange things with descriptor numbers. */
    if (num_heads > vq->vring.num) {
        error_report("Guest moved used index from %u to %u",
                     idx, vring_avail_idx(vq));
        exit(1);
    }
    /* On success, callers read a descriptor at vq->last_avail_idx.
     * Make sure descriptor read does not bypass avail index read. */
    if (num_heads) {
        smp_rmb();
    }

    return num_heads;
}

static unsigned int virtqueue_get_head(VirtQueue *vq, unsigned int idx)
{
    unsigned int head;

    /* Grab the next descriptor number they're advertising, and increment
     * the index we've seen. */
    head = vring_avail_ring(vq, idx % vq->vring.num);

    /* If their number is silly, that's a fatal mistake. */
    if (head >= vq->vring.num) {
        error_report("Guest says index %u is available", head);
        exit(1);
    }

    return head;
}

static unsigned virtqueue_next_desc(hwaddr desc_pa,
                                    unsigned int i, unsigned int max)
{
    unsigned int next;

    /* If this descriptor says it doesn't chain, we're done. */
    if (!(vring_desc_flags(desc_pa, i) & VRING_DESC_F_NEXT))
        return max;

    /* Check they're not leading us off end of descriptors. */
    next = vring_desc_next(desc_pa, i);
    /* Make sure compiler knows to grab that: we don't want it changing! */
    smp_wmb();

    if (next >= max) {
        error_report("Desc next is %u", next);
        exit(1);
    }

    return next;
}

void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
                               unsigned int *out_bytes,
                               unsigned max_in_bytes, unsigned max_out_bytes)
{
    unsigned int idx;
    unsigned int total_bufs, in_total, out_total;

    idx = vq->last_avail_idx;

    total_bufs = in_total = out_total = 0;
    while (virtqueue_num_heads(vq, idx)) {
        unsigned int max, num_bufs, indirect = 0;
        hwaddr desc_pa;
        int i;

        max = vq->vring.num;
        num_bufs = total_bufs;
        i = virtqueue_get_head(vq, idx++);
        desc_pa = vq->vring.desc;

        if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_INDIRECT) {
            if (vring_desc_len(desc_pa, i) % sizeof(VRingDesc)) {
                error_report("Invalid size for indirect buffer table");
                exit(1);
            }

            /* If we've got too many, that implies a descriptor loop. */
            if (num_bufs >= max) {
                error_report("Looped descriptor");
                exit(1);
            }

            /* loop over the indirect descriptor table */
            indirect = 1;
            max = vring_desc_len(desc_pa, i) / sizeof(VRingDesc);
            num_bufs = i = 0;
            desc_pa = vring_desc_addr(desc_pa, i);
        }

        do {
            /* If we've got too many, that implies a descriptor loop. */
            if (++num_bufs > max) {
                error_report("Looped descriptor");
                exit(1);
            }

            if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_WRITE) {
                in_total += vring_desc_len(desc_pa, i);
            } else {
                out_total += vring_desc_len(desc_pa, i);
            }
            if (in_total >= max_in_bytes && out_total >= max_out_bytes) {
                goto done;
            }
        } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max);

        if (!indirect)
            total_bufs = num_bufs;
        else
            total_bufs++;
    }
done:
    if (in_bytes) {
        *in_bytes = in_total;
    }
    if (out_bytes) {
        *out_bytes = out_total;
    }
}

int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes,
                          unsigned int out_bytes)
{
    unsigned int in_total, out_total;

    virtqueue_get_avail_bytes(vq, &in_total, &out_total, in_bytes, out_bytes);
    return in_bytes <= in_total && out_bytes <= out_total;
}

void virtqueue_map_sg(struct iovec *sg, hwaddr *addr,
    size_t num_sg, int is_write)
{
    unsigned int i;
    hwaddr len;

    for (i = 0; i < num_sg; i++) {
        len = sg[i].iov_len;
        sg[i].iov_base = cpu_physical_memory_map(addr[i], &len, is_write);
        if (sg[i].iov_base == NULL || len != sg[i].iov_len) {
            error_report("virtio: trying to map MMIO memory");
            exit(1);
        }
    }
}

int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
{
    unsigned int i, head, max;
    hwaddr desc_pa = vq->vring.desc;

    if (!virtqueue_num_heads(vq, vq->last_avail_idx))
        return 0;

    /* When we start there are none of either input nor output. */
    elem->out_num = elem->in_num = 0;

    max = vq->vring.num;

    i = head = virtqueue_get_head(vq, vq->last_avail_idx++);
    if (vq->vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
        vring_avail_event(vq, vring_avail_idx(vq));
    }

    if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_INDIRECT) {
        if (vring_desc_len(desc_pa, i) % sizeof(VRingDesc)) {
            error_report("Invalid size for indirect buffer table");
            exit(1);
        }

        /* loop over the indirect descriptor table */
        max = vring_desc_len(desc_pa, i) / sizeof(VRingDesc);
        desc_pa = vring_desc_addr(desc_pa, i);
        i = 0;
    }

    /* Collect all the descriptors */
    do {
        struct iovec *sg;

        if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_WRITE) {
            if (elem->in_num >= ARRAY_SIZE(elem->in_sg)) {
                error_report("Too many write descriptors in indirect table");
                exit(1);
            }
            elem->in_addr[elem->in_num] = vring_desc_addr(desc_pa, i);
            sg = &elem->in_sg[elem->in_num++];
        } else {
            if (elem->out_num >= ARRAY_SIZE(elem->out_sg)) {
                error_report("Too many read descriptors in indirect table");
                exit(1);
            }
            elem->out_addr[elem->out_num] = vring_desc_addr(desc_pa, i);
            sg = &elem->out_sg[elem->out_num++];
        }

        sg->iov_len = vring_desc_len(desc_pa, i);

        /* If we've got too many, that implies a descriptor loop. */
        if ((elem->in_num + elem->out_num) > max) {
            error_report("Looped descriptor");
            exit(1);
        }
    } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max);

    /* Now map what we have collected */
    virtqueue_map_sg(elem->in_sg, elem->in_addr, elem->in_num, 1);
    virtqueue_map_sg(elem->out_sg, elem->out_addr, elem->out_num, 0);

    elem->index = head;

    vq->inuse++;

    trace_virtqueue_pop(vq, elem, elem->in_num, elem->out_num);
    return elem->in_num + elem->out_num;
}

/* virtio device */
static void virtio_notify_vector(VirtIODevice *vdev, uint16_t vector)
{
    if (vdev->binding->notify) {
        vdev->binding->notify(vdev->binding_opaque, vector);
    }
}

void virtio_update_irq(VirtIODevice *vdev)
{
    virtio_notify_vector(vdev, VIRTIO_NO_VECTOR);
}

void virtio_set_status(VirtIODevice *vdev, uint8_t val)
{
    trace_virtio_set_status(vdev, val);

    if (vdev->set_status) {
        vdev->set_status(vdev, val);
    }
    vdev->status = val;
}

void virtio_reset(void *opaque)
{
    VirtIODevice *vdev = opaque;
    int i;

    virtio_set_status(vdev, 0);

    if (vdev->reset)
        vdev->reset(vdev);

    vdev->guest_features = 0;
    vdev->queue_sel = 0;
    vdev->status = 0;
    vdev->isr = 0;
    vdev->config_vector = VIRTIO_NO_VECTOR;
    virtio_notify_vector(vdev, vdev->config_vector);

    for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
        vdev->vq[i].vring.desc = 0;
        vdev->vq[i].vring.avail = 0;
        vdev->vq[i].vring.used = 0;
        vdev->vq[i].last_avail_idx = 0;
        vdev->vq[i].pa = 0;
        vdev->vq[i].vector = VIRTIO_NO_VECTOR;
        vdev->vq[i].signalled_used = 0;
        vdev->vq[i].signalled_used_valid = false;
        vdev->vq[i].notification = true;
    }
}

uint32_t virtio_config_readb(VirtIODevice *vdev, uint32_t addr)
{
    uint8_t val;

    vdev->get_config(vdev, vdev->config);

    if (addr > (vdev->config_len - sizeof(val)))
        return (uint32_t)-1;

    val = ldub_p(vdev->config + addr);
    return val;
}

uint32_t virtio_config_readw(VirtIODevice *vdev, uint32_t addr)
{
    uint16_t val;

    vdev->get_config(vdev, vdev->config);

    if (addr > (vdev->config_len - sizeof(val)))
        return (uint32_t)-1;

    val = lduw_p(vdev->config + addr);
    return val;
}

uint32_t virtio_config_readl(VirtIODevice *vdev, uint32_t addr)
{
    uint32_t val;

    vdev->get_config(vdev, vdev->config);

    if (addr > (vdev->config_len - sizeof(val)))
        return (uint32_t)-1;

    val = ldl_p(vdev->config + addr);
    return val;
}

void virtio_config_writeb(VirtIODevice *vdev, uint32_t addr, uint32_t data)
{
    uint8_t val = data;

    if (addr > (vdev->config_len - sizeof(val)))
        return;

    stb_p(vdev->config + addr, val);

    if (vdev->set_config)
        vdev->set_config(vdev, vdev->config);
}

void virtio_config_writew(VirtIODevice *vdev, uint32_t addr, uint32_t data)
{
    uint16_t val = data;

    if (addr > (vdev->config_len - sizeof(val)))
        return;

    stw_p(vdev->config + addr, val);

    if (vdev->set_config)
        vdev->set_config(vdev, vdev->config);
}

void virtio_config_writel(VirtIODevice *vdev, uint32_t addr, uint32_t data)
{
    uint32_t val = data;

    if (addr > (vdev->config_len - sizeof(val)))
        return;

    stl_p(vdev->config + addr, val);

    if (vdev->set_config)
        vdev->set_config(vdev, vdev->config);
}

void virtio_queue_set_addr(VirtIODevice *vdev, int n, hwaddr addr)
{
    vdev->vq[n].pa = addr;
    virtqueue_init(&vdev->vq[n]);
}

hwaddr virtio_queue_get_addr(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].pa;
}

int virtio_queue_get_num(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].vring.num;
}

int virtio_queue_get_id(VirtQueue *vq)
{
    VirtIODevice *vdev = vq->vdev;
    assert(vq >= &vdev->vq[0] && vq < &vdev->vq[VIRTIO_PCI_QUEUE_MAX]);
    return vq - &vdev->vq[0];
}

void virtio_queue_notify_vq(VirtQueue *vq)
{
    if (vq->vring.desc) {
        VirtIODevice *vdev = vq->vdev;
        trace_virtio_queue_notify(vdev, vq - vdev->vq, vq);
        vq->handle_output(vdev, vq);
    }
}

void virtio_queue_notify(VirtIODevice *vdev, int n)
{
    virtio_queue_notify_vq(&vdev->vq[n]);
}

uint16_t virtio_queue_vector(VirtIODevice *vdev, int n)
{
    return n < VIRTIO_PCI_QUEUE_MAX ? vdev->vq[n].vector :
        VIRTIO_NO_VECTOR;
}

void virtio_queue_set_vector(VirtIODevice *vdev, int n, uint16_t vector)
{
    if (n < VIRTIO_PCI_QUEUE_MAX)
        vdev->vq[n].vector = vector;
}

VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size,
                            void (*handle_output)(VirtIODevice *, VirtQueue *))
{
    int i;

    for (i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
        if (vdev->vq[i].vring.num == 0)
            break;
    }

    if (i == VIRTIO_PCI_QUEUE_MAX || queue_size > VIRTQUEUE_MAX_SIZE)
        abort();

    vdev->vq[i].vring.num = queue_size;
    vdev->vq[i].handle_output = handle_output;

    return &vdev->vq[i];
}

void virtio_irq(VirtQueue *vq)
{
    trace_virtio_irq(vq);
    vq->vdev->isr |= 0x01;
    virtio_notify_vector(vq->vdev, vq->vector);
}

/* Assuming a given event_idx value from the other size, if
 * we have just incremented index from old to new_idx,
 * should we trigger an event? */
static inline int vring_need_event(uint16_t event, uint16_t new, uint16_t old)
{
	/* Note: Xen has similar logic for notification hold-off
	 * in include/xen/interface/io/ring.h with req_event and req_prod
	 * corresponding to event_idx + 1 and new respectively.
	 * Note also that req_event and req_prod in Xen start at 1,
	 * event indexes in virtio start at 0. */
	return (uint16_t)(new - event - 1) < (uint16_t)(new - old);
}

static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq)
{
    uint16_t old, new;
    bool v;
    /* We need to expose used array entries before checking used event. */
    smp_mb();
    /* Always notify when queue is empty (when feature acknowledge) */
    if (((vdev->guest_features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) &&
         !vq->inuse && vring_avail_idx(vq) == vq->last_avail_idx)) {
        return true;
    }

    if (!(vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX))) {
        return !(vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT);
    }

    v = vq->signalled_used_valid;
    vq->signalled_used_valid = true;
    old = vq->signalled_used;
    new = vq->signalled_used = vring_used_idx(vq);
    return !v || vring_need_event(vring_used_event(vq), new, old);
}

void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
{
    if (!vring_notify(vdev, vq)) {
        return;
    }

    trace_virtio_notify(vdev, vq);
    vdev->isr |= 0x01;
    virtio_notify_vector(vdev, vq->vector);
}

void virtio_notify_config(VirtIODevice *vdev)
{
    if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK))
        return;

    vdev->isr |= 0x03;
    virtio_notify_vector(vdev, vdev->config_vector);
}

void virtio_save(VirtIODevice *vdev, QEMUFile *f)
{
    int i;

    if (vdev->binding->save_config)
        vdev->binding->save_config(vdev->binding_opaque, f);

    qemu_put_8s(f, &vdev->status);
    qemu_put_8s(f, &vdev->isr);
    qemu_put_be16s(f, &vdev->queue_sel);
    qemu_put_be32s(f, &vdev->guest_features);
    qemu_put_be32(f, vdev->config_len);
    qemu_put_buffer(f, vdev->config, vdev->config_len);

    for (i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
        if (vdev->vq[i].vring.num == 0)
            break;
    }

    qemu_put_be32(f, i);

    for (i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
        if (vdev->vq[i].vring.num == 0)
            break;

        qemu_put_be32(f, vdev->vq[i].vring.num);
        qemu_put_be64(f, vdev->vq[i].pa);
        qemu_put_be16s(f, &vdev->vq[i].last_avail_idx);
        if (vdev->binding->save_queue)
            vdev->binding->save_queue(vdev->binding_opaque, i, f);
    }
}

int virtio_set_features(VirtIODevice *vdev, uint32_t val)
{
    uint32_t supported_features =
        vdev->binding->get_features(vdev->binding_opaque);
    bool bad = (val & ~supported_features) != 0;

    val &= supported_features;
    if (vdev->set_features) {
        vdev->set_features(vdev, val);
    }
    vdev->guest_features = val;
    return bad ? -1 : 0;
}

int virtio_load(VirtIODevice *vdev, QEMUFile *f)
{
    int num, i, ret;
    uint32_t features;
    uint32_t supported_features;

    if (vdev->binding->load_config) {
        ret = vdev->binding->load_config(vdev->binding_opaque, f);
        if (ret)
            return ret;
    }

    qemu_get_8s(f, &vdev->status);
    qemu_get_8s(f, &vdev->isr);
    qemu_get_be16s(f, &vdev->queue_sel);
    qemu_get_be32s(f, &features);

    if (virtio_set_features(vdev, features) < 0) {
        supported_features = vdev->binding->get_features(vdev->binding_opaque);
        error_report("Features 0x%x unsupported. Allowed features: 0x%x",
                     features, supported_features);
        return -1;
    }
    vdev->config_len = qemu_get_be32(f);
    qemu_get_buffer(f, vdev->config, vdev->config_len);

    num = qemu_get_be32(f);

    for (i = 0; i < num; i++) {
        vdev->vq[i].vring.num = qemu_get_be32(f);
        vdev->vq[i].pa = qemu_get_be64(f);
        qemu_get_be16s(f, &vdev->vq[i].last_avail_idx);
        vdev->vq[i].signalled_used_valid = false;
        vdev->vq[i].notification = true;

        if (vdev->vq[i].pa) {
            uint16_t nheads;
            virtqueue_init(&vdev->vq[i]);
            nheads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx;
            /* Check it isn't doing very strange things with descriptor numbers. */
            if (nheads > vdev->vq[i].vring.num) {
                error_report("VQ %d size 0x%x Guest index 0x%x "
                             "inconsistent with Host index 0x%x: delta 0x%x",
                             i, vdev->vq[i].vring.num,
                             vring_avail_idx(&vdev->vq[i]),
                             vdev->vq[i].last_avail_idx, nheads);
                return -1;
            }
        } else if (vdev->vq[i].last_avail_idx) {
            error_report("VQ %d address 0x0 "
                         "inconsistent with Host index 0x%x",
                         i, vdev->vq[i].last_avail_idx);
                return -1;
	}
        if (vdev->binding->load_queue) {
            ret = vdev->binding->load_queue(vdev->binding_opaque, i, f);
            if (ret)
                return ret;
        }
    }

    virtio_notify_vector(vdev, VIRTIO_NO_VECTOR);
    return 0;
}

void virtio_cleanup(VirtIODevice *vdev)
{
    qemu_del_vm_change_state_handler(vdev->vmstate);
    g_free(vdev->config);
    g_free(vdev->vq);
    g_free(vdev);
}

static void virtio_vmstate_change(void *opaque, int running, RunState state)
{
    VirtIODevice *vdev = opaque;
    bool backend_run = running && (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK);
    vdev->vm_running = running;

    if (backend_run) {
        virtio_set_status(vdev, vdev->status);
    }

    if (vdev->binding->vmstate_change) {
        vdev->binding->vmstate_change(vdev->binding_opaque, backend_run);
    }

    if (!backend_run) {
        virtio_set_status(vdev, vdev->status);
    }
}

VirtIODevice *virtio_common_init(const char *name, uint16_t device_id,
                                 size_t config_size, size_t struct_size)
{
    VirtIODevice *vdev;
    int i;

    vdev = g_malloc0(struct_size);

    vdev->device_id = device_id;
    vdev->status = 0;
    vdev->isr = 0;
    vdev->queue_sel = 0;
    vdev->config_vector = VIRTIO_NO_VECTOR;
    vdev->vq = g_malloc0(sizeof(VirtQueue) * VIRTIO_PCI_QUEUE_MAX);
    vdev->vm_running = runstate_is_running();
    for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
        vdev->vq[i].vector = VIRTIO_NO_VECTOR;
        vdev->vq[i].vdev = vdev;
    }

    vdev->name = name;
    vdev->config_len = config_size;
    if (vdev->config_len)
        vdev->config = g_malloc0(config_size);
    else
        vdev->config = NULL;

    vdev->vmstate = qemu_add_vm_change_state_handler(virtio_vmstate_change, vdev);

    return vdev;
}

void virtio_bind_device(VirtIODevice *vdev, const VirtIOBindings *binding,
                        void *opaque)
{
    vdev->binding = binding;
    vdev->binding_opaque = opaque;
}

hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].vring.desc;
}

hwaddr virtio_queue_get_avail_addr(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].vring.avail;
}

hwaddr virtio_queue_get_used_addr(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].vring.used;
}

hwaddr virtio_queue_get_ring_addr(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].vring.desc;
}

hwaddr virtio_queue_get_desc_size(VirtIODevice *vdev, int n)
{
    return sizeof(VRingDesc) * vdev->vq[n].vring.num;
}

hwaddr virtio_queue_get_avail_size(VirtIODevice *vdev, int n)
{
    return offsetof(VRingAvail, ring) +
        sizeof(uint64_t) * vdev->vq[n].vring.num;
}

hwaddr virtio_queue_get_used_size(VirtIODevice *vdev, int n)
{
    return offsetof(VRingUsed, ring) +
        sizeof(VRingUsedElem) * vdev->vq[n].vring.num;
}

hwaddr virtio_queue_get_ring_size(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].vring.used - vdev->vq[n].vring.desc +
	    virtio_queue_get_used_size(vdev, n);
}

uint16_t virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n)
{
    return vdev->vq[n].last_avail_idx;
}

void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n, uint16_t idx)
{
    vdev->vq[n].last_avail_idx = idx;
}

VirtQueue *virtio_get_queue(VirtIODevice *vdev, int n)
{
    return vdev->vq + n;
}

static void virtio_queue_guest_notifier_read(EventNotifier *n)
{
    VirtQueue *vq = container_of(n, VirtQueue, guest_notifier);
    if (event_notifier_test_and_clear(n)) {
        virtio_irq(vq);
    }
}

void virtio_queue_set_guest_notifier_fd_handler(VirtQueue *vq, bool assign,
                                                bool with_irqfd)
{
    if (assign && !with_irqfd) {
        event_notifier_set_handler(&vq->guest_notifier,
                                   virtio_queue_guest_notifier_read);
    } else {
        event_notifier_set_handler(&vq->guest_notifier, NULL);
    }
    if (!assign) {
        /* Test and clear notifier before closing it,
         * in case poll callback didn't have time to run. */
        virtio_queue_guest_notifier_read(&vq->guest_notifier);
    }
}

EventNotifier *virtio_queue_get_guest_notifier(VirtQueue *vq)
{
    return &vq->guest_notifier;
}

static void virtio_queue_host_notifier_read(EventNotifier *n)
{
    VirtQueue *vq = container_of(n, VirtQueue, host_notifier);
    if (event_notifier_test_and_clear(n)) {
        virtio_queue_notify_vq(vq);
    }
}

void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign,
                                               bool set_handler)
{
    if (assign && set_handler) {
        event_notifier_set_handler(&vq->host_notifier,
                                   virtio_queue_host_notifier_read);
    } else {
        event_notifier_set_handler(&vq->host_notifier, NULL);
    }
    if (!assign) {
        /* Test and clear notifier before after disabling event,
         * in case poll callback didn't have time to run. */
        virtio_queue_host_notifier_read(&vq->host_notifier);
    }
}

EventNotifier *virtio_queue_get_host_notifier(VirtQueue *vq)
{
    return &vq->host_notifier;
}