aboutsummaryrefslogtreecommitdiff
path: root/hw/virtio.c
blob: 8a72d8d216c0cc7b63829cd5323488ce2476ba96 (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
/*
 * 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 "virtio.h"
#include "sysemu.h"

/* from Linux's linux/virtio_pci.h */

/* A 32-bit r/o bitmask of the features supported by the host */
#define VIRTIO_PCI_HOST_FEATURES        0

/* A 32-bit r/w bitmask of features activated by the guest */
#define VIRTIO_PCI_GUEST_FEATURES       4

/* A 32-bit r/w PFN for the currently selected queue */
#define VIRTIO_PCI_QUEUE_PFN            8

/* A 16-bit r/o queue size for the currently selected queue */
#define VIRTIO_PCI_QUEUE_NUM            12

/* A 16-bit r/w queue selector */
#define VIRTIO_PCI_QUEUE_SEL            14

/* A 16-bit r/w queue notifier */
#define VIRTIO_PCI_QUEUE_NOTIFY         16

/* An 8-bit device status register.  */
#define VIRTIO_PCI_STATUS               18

/* An 8-bit r/o interrupt status register.  Reading the value will return the
 * current contents of the ISR and will also clear it.  This is effectively
 * a read-and-acknowledge. */
#define VIRTIO_PCI_ISR                  19

#define VIRTIO_PCI_CONFIG               20

/* Virtio ABI version, if we increment this, we break the guest driver. */
#define VIRTIO_PCI_ABI_VERSION          0

/* How many bits to shift physical queue address written to QUEUE_PFN.
 * 12 is historical, and due to x86 page size. */
#define VIRTIO_PCI_QUEUE_ADDR_SHIFT    12

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

/* QEMU doesn't strictly need write barriers since everything runs in
 * lock-step.  We'll leave the calls to wmb() in though to make it obvious for
 * KVM or if kqemu gets SMP support.
 */
#define wmb() do { } while (0)

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;
    target_phys_addr_t desc;
    target_phys_addr_t avail;
    target_phys_addr_t used;
} VRing;

struct VirtQueue
{
    VRing vring;
    uint32_t pfn;
    uint16_t last_avail_idx;
    int inuse;
    void (*handle_output)(VirtIODevice *vdev, VirtQueue *vq);
};

#define VIRTIO_PCI_QUEUE_MAX        16

/* virt queue functions */
static void virtqueue_init(VirtQueue *vq, target_phys_addr_t 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(VirtQueue *vq, int i)
{
    target_phys_addr_t pa;
    pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, addr);
    return ldq_phys(pa);
}

static inline uint32_t vring_desc_len(VirtQueue *vq, int i)
{
    target_phys_addr_t pa;
    pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, len);
    return ldl_phys(pa);
}

static inline uint16_t vring_desc_flags(VirtQueue *vq, int i)
{
    target_phys_addr_t pa;
    pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, flags);
    return lduw_phys(pa);
}

static inline uint16_t vring_desc_next(VirtQueue *vq, int i)
{
    target_phys_addr_t pa;
    pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, next);
    return lduw_phys(pa);
}

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

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

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

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

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

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

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

void virtio_queue_set_notification(VirtQueue *vq, int enable)
{
    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);
}

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;

    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 += elem->in_sg[i].iov_len;
    }

    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)
{
    /* Make sure buffer is written before we update index. */
    wmb();
    vring_used_idx_increment(vq, count);
    vq->inuse -= count;
}

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) {
        fprintf(stderr, "Guest moved used index from %u to %u",
                idx, vring_avail_idx(vq));
        exit(1);
    }

    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) {
        fprintf(stderr, "Guest says index %u is available", head);
        exit(1);
    }

    return head;
}

static unsigned virtqueue_next_desc(VirtQueue *vq, unsigned int i)
{
    unsigned int next;

    /* If this descriptor says it doesn't chain, we're done. */
    if (!(vring_desc_flags(vq, i) & VRING_DESC_F_NEXT))
        return vq->vring.num;

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

    if (next >= vq->vring.num) {
        fprintf(stderr, "Desc next is %u", next);
        exit(1);
    }

    return next;
}

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

    idx = vq->last_avail_idx;

    num_bufs = in_total = out_total = 0;
    while (virtqueue_num_heads(vq, idx)) {
        int i;

        i = virtqueue_get_head(vq, idx++);
        do {
            /* If we've got too many, that implies a descriptor loop. */
            if (++num_bufs > vq->vring.num) {
                fprintf(stderr, "Looped descriptor");
                exit(1);
            }

            if (vring_desc_flags(vq, i) & VRING_DESC_F_WRITE) {
                if (in_bytes > 0 &&
                    (in_total += vring_desc_len(vq, i)) >= in_bytes)
                    return 1;
            } else {
                if (out_bytes > 0 &&
                    (out_total += vring_desc_len(vq, i)) >= out_bytes)
                    return 1;
            }
        } while ((i = virtqueue_next_desc(vq, i)) != vq->vring.num);
    }

    return 0;
}

int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
{
    unsigned int i, head;
    target_phys_addr_t len;

    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;

    i = head = virtqueue_get_head(vq, vq->last_avail_idx++);
    do {
        struct iovec *sg;
        int is_write = 0;

        if (vring_desc_flags(vq, i) & VRING_DESC_F_WRITE) {
            elem->in_addr[elem->in_num] = vring_desc_addr(vq, i);
            sg = &elem->in_sg[elem->in_num++];
            is_write = 1;
        } else
            sg = &elem->out_sg[elem->out_num++];

        /* Grab the first descriptor, and check it's OK. */
        sg->iov_len = vring_desc_len(vq, i);
        len = sg->iov_len;

        sg->iov_base = cpu_physical_memory_map(vring_desc_addr(vq, i), &len, is_write);

        if (sg->iov_base == NULL || len != sg->iov_len) {
            fprintf(stderr, "virtio: trying to map MMIO memory\n");
            exit(1);
        }

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

    elem->index = head;

    vq->inuse++;

    return elem->in_num + elem->out_num;
}

/* virtio device */

static VirtIODevice *to_virtio_device(PCIDevice *pci_dev)
{
    return (VirtIODevice *)pci_dev;
}

static void virtio_update_irq(VirtIODevice *vdev)
{
    qemu_set_irq(vdev->pci_dev.irq[0], vdev->isr & 1);
}

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

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

    vdev->features = 0;
    vdev->queue_sel = 0;
    vdev->status = 0;
    vdev->isr = 0;
    virtio_update_irq(vdev);

    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].pfn = 0;
    }
}

static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
{
    VirtIODevice *vdev = to_virtio_device(opaque);
    ram_addr_t pa;

    addr -= vdev->addr;

    switch (addr) {
    case VIRTIO_PCI_GUEST_FEATURES:
        if (vdev->set_features)
            vdev->set_features(vdev, val);
        vdev->features = val;
        break;
    case VIRTIO_PCI_QUEUE_PFN:
        pa = (ram_addr_t)val << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
        vdev->vq[vdev->queue_sel].pfn = val;
        if (pa == 0) {
            virtio_reset(vdev);
        } else {
            virtqueue_init(&vdev->vq[vdev->queue_sel], pa);
        }
        break;
    case VIRTIO_PCI_QUEUE_SEL:
        if (val < VIRTIO_PCI_QUEUE_MAX)
            vdev->queue_sel = val;
        break;
    case VIRTIO_PCI_QUEUE_NOTIFY:
        if (val < VIRTIO_PCI_QUEUE_MAX && vdev->vq[val].vring.desc)
            vdev->vq[val].handle_output(vdev, &vdev->vq[val]);
        break;
    case VIRTIO_PCI_STATUS:
        vdev->status = val & 0xFF;
        if (vdev->status == 0)
            virtio_reset(vdev);
        break;
    }
}

static uint32_t virtio_ioport_read(void *opaque, uint32_t addr)
{
    VirtIODevice *vdev = to_virtio_device(opaque);
    uint32_t ret = 0xFFFFFFFF;

    addr -= vdev->addr;

    switch (addr) {
    case VIRTIO_PCI_HOST_FEATURES:
        ret = vdev->get_features(vdev);
        ret |= (1 << VIRTIO_F_NOTIFY_ON_EMPTY);
        break;
    case VIRTIO_PCI_GUEST_FEATURES:
        ret = vdev->features;
        break;
    case VIRTIO_PCI_QUEUE_PFN:
        ret = vdev->vq[vdev->queue_sel].pfn;
        break;
    case VIRTIO_PCI_QUEUE_NUM:
        ret = vdev->vq[vdev->queue_sel].vring.num;
        break;
    case VIRTIO_PCI_QUEUE_SEL:
        ret = vdev->queue_sel;
        break;
    case VIRTIO_PCI_STATUS:
        ret = vdev->status;
        break;
    case VIRTIO_PCI_ISR:
        /* reading from the ISR also clears it. */
        ret = vdev->isr;
        vdev->isr = 0;
        virtio_update_irq(vdev);
        break;
    default:
        break;
    }

    return ret;
}

static uint32_t virtio_config_readb(void *opaque, uint32_t addr)
{
    VirtIODevice *vdev = opaque;
    uint8_t val;

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

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

    memcpy(&val, vdev->config + addr, sizeof(val));
    return val;
}

static uint32_t virtio_config_readw(void *opaque, uint32_t addr)
{
    VirtIODevice *vdev = opaque;
    uint16_t val;

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

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

    memcpy(&val, vdev->config + addr, sizeof(val));
    return val;
}

static uint32_t virtio_config_readl(void *opaque, uint32_t addr)
{
    VirtIODevice *vdev = opaque;
    uint32_t val;

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

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

    memcpy(&val, vdev->config + addr, sizeof(val));
    return val;
}

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

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

    memcpy(vdev->config + addr, &val, sizeof(val));

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

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

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

    memcpy(vdev->config + addr, &val, sizeof(val));

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

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

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

    memcpy(vdev->config + addr, &val, sizeof(val));

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

static void virtio_map(PCIDevice *pci_dev, int region_num,
                       uint32_t addr, uint32_t size, int type)
{
    VirtIODevice *vdev = to_virtio_device(pci_dev);
    int i;

    vdev->addr = addr;
    for (i = 0; i < 3; i++) {
        register_ioport_write(addr, 20, 1 << i, virtio_ioport_write, vdev);
        register_ioport_read(addr, 20, 1 << i, virtio_ioport_read, vdev);
    }

    if (vdev->config_len) {
        register_ioport_write(addr + 20, vdev->config_len, 1,
                              virtio_config_writeb, vdev);
        register_ioport_write(addr + 20, vdev->config_len, 2,
                              virtio_config_writew, vdev);
        register_ioport_write(addr + 20, vdev->config_len, 4,
                              virtio_config_writel, vdev);
        register_ioport_read(addr + 20, vdev->config_len, 1,
                             virtio_config_readb, vdev);
        register_ioport_read(addr + 20, vdev->config_len, 2,
                             virtio_config_readw, vdev);
        register_ioport_read(addr + 20, vdev->config_len, 4,
                             virtio_config_readl, vdev);

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

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_notify(VirtIODevice *vdev, VirtQueue *vq)
{
    /* Always notify when queue is empty (when feature acknowledge) */
    if ((vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT) &&
        (!(vdev->features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) ||
         (vq->inuse || vring_avail_idx(vq) != vq->last_avail_idx)))
        return;

    vdev->isr |= 0x01;
    virtio_update_irq(vdev);
}

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

    vdev->isr |= 0x03;
    virtio_update_irq(vdev);
}

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

    pci_device_save(&vdev->pci_dev, f);

    qemu_put_be32s(f, &vdev->addr);
    qemu_put_8s(f, &vdev->status);
    qemu_put_8s(f, &vdev->isr);
    qemu_put_be16s(f, &vdev->queue_sel);
    qemu_put_be32s(f, &vdev->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_be32s(f, &vdev->vq[i].pfn);
        qemu_put_be16s(f, &vdev->vq[i].last_avail_idx);
    }
}

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

    pci_device_load(&vdev->pci_dev, f);

    qemu_get_be32s(f, &vdev->addr);
    qemu_get_8s(f, &vdev->status);
    qemu_get_8s(f, &vdev->isr);
    qemu_get_be16s(f, &vdev->queue_sel);
    qemu_get_be32s(f, &vdev->features);
    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);
        qemu_get_be32s(f, &vdev->vq[i].pfn);
        qemu_get_be16s(f, &vdev->vq[i].last_avail_idx);

        if (vdev->vq[i].pfn) {
            target_phys_addr_t pa;

            pa = (ram_addr_t)vdev->vq[i].pfn << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
            virtqueue_init(&vdev->vq[i], pa);
        }
    }

    virtio_update_irq(vdev);
}

VirtIODevice *virtio_init_pci(PCIBus *bus, const char *name,
                              uint16_t vendor, uint16_t device,
                              uint16_t subvendor, uint16_t subdevice,
                              uint16_t class_code, uint8_t pif,
                              size_t config_size, size_t struct_size)
{
    VirtIODevice *vdev;
    PCIDevice *pci_dev;
    uint8_t *config;
    uint32_t size;

    pci_dev = pci_register_device(bus, name, struct_size,
                                  -1, NULL, NULL);
    if (!pci_dev)
        return NULL;

    vdev = to_virtio_device(pci_dev);

    vdev->status = 0;
    vdev->isr = 0;
    vdev->queue_sel = 0;
    vdev->vq = qemu_mallocz(sizeof(VirtQueue) * VIRTIO_PCI_QUEUE_MAX);

    config = pci_dev->config;
    pci_config_set_vendor_id(config, vendor);
    pci_config_set_device_id(config, device);

    config[0x08] = VIRTIO_PCI_ABI_VERSION;

    config[0x09] = pif;
    pci_config_set_class(config, class_code);
    config[0x0e] = 0x00;

    config[0x2c] = subvendor & 0xFF;
    config[0x2d] = (subvendor >> 8) & 0xFF;
    config[0x2e] = subdevice & 0xFF;
    config[0x2f] = (subdevice >> 8) & 0xFF;

    config[0x3d] = 1;

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

    size = 20 + config_size;
    if (size & (size-1))
        size = 1 << qemu_fls(size);

    pci_register_io_region(pci_dev, 0, size, PCI_ADDRESS_SPACE_IO,
                           virtio_map);
    qemu_register_reset(virtio_reset, vdev);

    return vdev;
}