summaryrefslogtreecommitdiff
blob: 5b643561ef8e21231a5b7c8c509434d30cfb4efd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
/*
 * Virtio PCI Bindings
 *
 * Copyright IBM, Corp. 2007
 * Copyright (c) 2009 CodeSourcery
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *  Paul Brook        <paul@codesourcery.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include <inttypes.h>

#include "virtio.h"
#include "virtio-blk.h"
#include "virtio-net.h"
#include "virtio-serial.h"
#include "virtio-scsi.h"
#include "pci.h"
#include "qemu-error.h"
#include "msix.h"
#include "net.h"
#include "loader.h"
#include "kvm.h"
#include "blockdev.h"
#include "virtio-pci.h"
#include "range.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

/* MSI-X registers: only enabled if MSI-X is enabled. */
/* A 16-bit vector for configuration changes. */
#define VIRTIO_MSI_CONFIG_VECTOR        20
/* A 16-bit vector for selected queue notifications. */
#define VIRTIO_MSI_QUEUE_VECTOR         22

/* Config space size */
#define VIRTIO_PCI_CONFIG_NOMSI         20
#define VIRTIO_PCI_CONFIG_MSI           24
#define VIRTIO_PCI_REGION_SIZE(dev)     (msix_present(dev) ? \
                                         VIRTIO_PCI_CONFIG_MSI : \
                                         VIRTIO_PCI_CONFIG_NOMSI)

/* The remaining space is defined by each driver as the per-driver
 * configuration space */
#define VIRTIO_PCI_CONFIG(dev)          (msix_enabled(dev) ? \
                                         VIRTIO_PCI_CONFIG_MSI : \
                                         VIRTIO_PCI_CONFIG_NOMSI)

/* 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

/* Flags track per-device state like workarounds for quirks in older guests. */
#define VIRTIO_PCI_FLAG_BUS_MASTER_BUG  (1 << 0)

/* 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)

/* HACK for virtio to determine if it's running a big endian guest */
bool virtio_is_big_endian(void);

/* virtio device */

static void virtio_pci_notify(void *opaque, uint16_t vector)
{
    VirtIOPCIProxy *proxy = opaque;
    if (msix_enabled(&proxy->pci_dev))
        msix_notify(&proxy->pci_dev, vector);
    else
        qemu_set_irq(proxy->pci_dev.irq[0], proxy->vdev->isr & 1);
}

static void virtio_pci_save_config(void * opaque, QEMUFile *f)
{
    VirtIOPCIProxy *proxy = opaque;
    pci_device_save(&proxy->pci_dev, f);
    msix_save(&proxy->pci_dev, f);
    if (msix_present(&proxy->pci_dev))
        qemu_put_be16(f, proxy->vdev->config_vector);
}

static void virtio_pci_save_queue(void * opaque, int n, QEMUFile *f)
{
    VirtIOPCIProxy *proxy = opaque;
    if (msix_present(&proxy->pci_dev))
        qemu_put_be16(f, virtio_queue_vector(proxy->vdev, n));
}

static int virtio_pci_load_config(void * opaque, QEMUFile *f)
{
    VirtIOPCIProxy *proxy = opaque;
    int ret;
    ret = pci_device_load(&proxy->pci_dev, f);
    if (ret) {
        return ret;
    }
    msix_load(&proxy->pci_dev, f);
    if (msix_present(&proxy->pci_dev)) {
        qemu_get_be16s(f, &proxy->vdev->config_vector);
    } else {
        proxy->vdev->config_vector = VIRTIO_NO_VECTOR;
    }
    if (proxy->vdev->config_vector != VIRTIO_NO_VECTOR) {
        return msix_vector_use(&proxy->pci_dev, proxy->vdev->config_vector);
    }
    return 0;
}

static int virtio_pci_load_queue(void * opaque, int n, QEMUFile *f)
{
    VirtIOPCIProxy *proxy = opaque;
    uint16_t vector;
    if (msix_present(&proxy->pci_dev)) {
        qemu_get_be16s(f, &vector);
    } else {
        vector = VIRTIO_NO_VECTOR;
    }
    virtio_queue_set_vector(proxy->vdev, n, vector);
    if (vector != VIRTIO_NO_VECTOR) {
        return msix_vector_use(&proxy->pci_dev, vector);
    }
    return 0;
}

static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
                                                 int n, bool assign)
{
    VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
    EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
    int r = 0;

    if (assign) {
        r = event_notifier_init(notifier, 1);
        if (r < 0) {
            error_report("%s: unable to init event notifier: %d",
                         __func__, r);
            return r;
        }
        memory_region_add_eventfd(&proxy->bar, VIRTIO_PCI_QUEUE_NOTIFY, 2,
                                  true, n, event_notifier_get_fd(notifier));
    } else {
        memory_region_del_eventfd(&proxy->bar, VIRTIO_PCI_QUEUE_NOTIFY, 2,
                                  true, n, event_notifier_get_fd(notifier));
        /* Handle the race condition where the guest kicked and we deassigned
         * before we got around to handling the kick.
         */
        if (event_notifier_test_and_clear(notifier)) {
            virtio_queue_notify_vq(vq);
        }

        event_notifier_cleanup(notifier);
    }
    return r;
}

static void virtio_pci_host_notifier_read(void *opaque)
{
    VirtQueue *vq = opaque;
    EventNotifier *n = virtio_queue_get_host_notifier(vq);
    if (event_notifier_test_and_clear(n)) {
        virtio_queue_notify_vq(vq);
    }
}

static void virtio_pci_set_host_notifier_fd_handler(VirtIOPCIProxy *proxy,
                                                    int n, bool assign)
{
    VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
    EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
    if (assign) {
        qemu_set_fd_handler(event_notifier_get_fd(notifier),
                            virtio_pci_host_notifier_read, NULL, vq);
    } else {
        qemu_set_fd_handler(event_notifier_get_fd(notifier),
                            NULL, NULL, NULL);
    }
}

static void virtio_pci_start_ioeventfd(VirtIOPCIProxy *proxy)
{
    int n, r;

    if (!(proxy->flags & VIRTIO_PCI_FLAG_USE_IOEVENTFD) ||
        proxy->ioeventfd_disabled ||
        proxy->ioeventfd_started) {
        return;
    }

    for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
        if (!virtio_queue_get_num(proxy->vdev, n)) {
            continue;
        }

        r = virtio_pci_set_host_notifier_internal(proxy, n, true);
        if (r < 0) {
            goto assign_error;
        }

        virtio_pci_set_host_notifier_fd_handler(proxy, n, true);
    }
    proxy->ioeventfd_started = true;
    return;

assign_error:
    while (--n >= 0) {
        if (!virtio_queue_get_num(proxy->vdev, n)) {
            continue;
        }

        virtio_pci_set_host_notifier_fd_handler(proxy, n, false);
        r = virtio_pci_set_host_notifier_internal(proxy, n, false);
        assert(r >= 0);
    }
    proxy->ioeventfd_started = false;
    error_report("%s: failed. Fallback to a userspace (slower).", __func__);
}

static void virtio_pci_stop_ioeventfd(VirtIOPCIProxy *proxy)
{
    int r;
    int n;

    if (!proxy->ioeventfd_started) {
        return;
    }

    for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
        if (!virtio_queue_get_num(proxy->vdev, n)) {
            continue;
        }

        virtio_pci_set_host_notifier_fd_handler(proxy, n, false);
        r = virtio_pci_set_host_notifier_internal(proxy, n, false);
        assert(r >= 0);
    }
    proxy->ioeventfd_started = false;
}

void virtio_pci_reset(DeviceState *d)
{
    VirtIOPCIProxy *proxy = container_of(d, VirtIOPCIProxy, pci_dev.qdev);
    virtio_pci_stop_ioeventfd(proxy);
    virtio_reset(proxy->vdev);
    msix_reset(&proxy->pci_dev);
    proxy->flags &= ~VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
}

static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
{
    VirtIOPCIProxy *proxy = opaque;
    VirtIODevice *vdev = proxy->vdev;
    target_phys_addr_t pa;

    switch (addr) {
    case VIRTIO_PCI_GUEST_FEATURES:
	/* Guest does not negotiate properly?  We have to assume nothing. */
	if (val & (1 << VIRTIO_F_BAD_FEATURE)) {
            val = vdev->bad_features ? vdev->bad_features(vdev) : 0;
	}
        virtio_set_features(vdev, val);
        break;
    case VIRTIO_PCI_QUEUE_PFN:
        pa = (target_phys_addr_t)val << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
        if (pa == 0) {
            virtio_pci_stop_ioeventfd(proxy);
            virtio_reset(proxy->vdev);
            msix_unuse_all_vectors(&proxy->pci_dev);
        }
        else
            virtio_queue_set_addr(vdev, 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) {
            virtio_queue_notify(vdev, val);
        }
        break;
    case VIRTIO_PCI_STATUS:
        if (!(val & VIRTIO_CONFIG_S_DRIVER_OK)) {
            virtio_pci_stop_ioeventfd(proxy);
        }

        virtio_set_status(vdev, val & 0xFF);

        if (val & VIRTIO_CONFIG_S_DRIVER_OK) {
            virtio_pci_start_ioeventfd(proxy);
        }

        if (vdev->status == 0) {
            virtio_reset(proxy->vdev);
            msix_unuse_all_vectors(&proxy->pci_dev);
        }

        /* Linux before 2.6.34 sets the device as OK without enabling
           the PCI device bus master bit. In this case we need to disable
           some safety checks. */
        if ((val & VIRTIO_CONFIG_S_DRIVER_OK) &&
            !(proxy->pci_dev.config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
            proxy->flags |= VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
        }
        break;
    case VIRTIO_MSI_CONFIG_VECTOR:
        msix_vector_unuse(&proxy->pci_dev, vdev->config_vector);
        /* Make it possible for guest to discover an error took place. */
        if (msix_vector_use(&proxy->pci_dev, val) < 0)
            val = VIRTIO_NO_VECTOR;
        vdev->config_vector = val;
        break;
    case VIRTIO_MSI_QUEUE_VECTOR:
        msix_vector_unuse(&proxy->pci_dev,
                          virtio_queue_vector(vdev, vdev->queue_sel));
        /* Make it possible for guest to discover an error took place. */
        if (msix_vector_use(&proxy->pci_dev, val) < 0)
            val = VIRTIO_NO_VECTOR;
        virtio_queue_set_vector(vdev, vdev->queue_sel, val);
        break;
    default:
        error_report("%s: unexpected address 0x%x value 0x%x",
                     __func__, addr, val);
        break;
    }
}

static uint32_t virtio_ioport_read(VirtIOPCIProxy *proxy, uint32_t addr)
{
    VirtIODevice *vdev = proxy->vdev;
    uint32_t ret = 0xFFFFFFFF;

    switch (addr) {
    case VIRTIO_PCI_HOST_FEATURES:
        ret = proxy->host_features;
        break;
    case VIRTIO_PCI_GUEST_FEATURES:
        ret = vdev->guest_features;
        break;
    case VIRTIO_PCI_QUEUE_PFN:
        ret = virtio_queue_get_addr(vdev, vdev->queue_sel)
              >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
        break;
    case VIRTIO_PCI_QUEUE_NUM:
        ret = virtio_queue_get_num(vdev, vdev->queue_sel);
        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;
        qemu_set_irq(proxy->pci_dev.irq[0], 0);
        break;
    case VIRTIO_MSI_CONFIG_VECTOR:
        ret = vdev->config_vector;
        break;
    case VIRTIO_MSI_QUEUE_VECTOR:
        ret = virtio_queue_vector(vdev, vdev->queue_sel);
        break;
    default:
        break;
    }

    return ret;
}

static uint32_t virtio_pci_config_readb(void *opaque, uint32_t addr)
{
    VirtIOPCIProxy *proxy = opaque;
    uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
    if (addr < config)
        return virtio_ioport_read(proxy, addr);
    addr -= config;
    return virtio_config_readb(proxy->vdev, addr);
}

static uint32_t virtio_pci_config_readw(void *opaque, uint32_t addr)
{
    VirtIOPCIProxy *proxy = opaque;
    uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
    uint16_t val;
    if (addr < config)
        return virtio_ioport_read(proxy, addr);
    addr -= config;
    val = virtio_config_readw(proxy->vdev, addr);
    if (virtio_is_big_endian()) {
        /*
         * virtio is odd, ioports are LE but config space is target native
         * endian. However, in qemu, all PIO is LE, so we need to re-swap
         * on BE targets
         */
        val = bswap16(val);
    }
    return val;
}

static uint32_t virtio_pci_config_readl(void *opaque, uint32_t addr)
{
    VirtIOPCIProxy *proxy = opaque;
    uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
    uint32_t val;
    if (addr < config)
        return virtio_ioport_read(proxy, addr);
    addr -= config;
    val = virtio_config_readl(proxy->vdev, addr);
    if (virtio_is_big_endian()) {
        val = bswap32(val);
    }
    return val;
}

static void virtio_pci_config_writeb(void *opaque, uint32_t addr, uint32_t val)
{
    VirtIOPCIProxy *proxy = opaque;
    uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
    if (addr < config) {
        virtio_ioport_write(proxy, addr, val);
        return;
    }
    addr -= config;
    virtio_config_writeb(proxy->vdev, addr, val);
}

static void virtio_pci_config_writew(void *opaque, uint32_t addr, uint32_t val)
{
    VirtIOPCIProxy *proxy = opaque;
    uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
    if (addr < config) {
        virtio_ioport_write(proxy, addr, val);
        return;
    }
    addr -= config;
    if (virtio_is_big_endian()) {
        val = bswap16(val);
    }
    virtio_config_writew(proxy->vdev, addr, val);
}

static void virtio_pci_config_writel(void *opaque, uint32_t addr, uint32_t val)
{
    VirtIOPCIProxy *proxy = opaque;
    uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
    if (addr < config) {
        virtio_ioport_write(proxy, addr, val);
        return;
    }
    addr -= config;
    if (virtio_is_big_endian()) {
        val = bswap32(val);
    }
    virtio_config_writel(proxy->vdev, addr, val);
}

static const MemoryRegionPortio virtio_portio[] = {
    { 0, 0x10000, 1, .write = virtio_pci_config_writeb, },
    { 0, 0x10000, 2, .write = virtio_pci_config_writew, },
    { 0, 0x10000, 4, .write = virtio_pci_config_writel, },
    { 0, 0x10000, 1, .read = virtio_pci_config_readb, },
    { 0, 0x10000, 2, .read = virtio_pci_config_readw, },
    { 0, 0x10000, 4, .read = virtio_pci_config_readl, },
    PORTIO_END_OF_LIST()
};

static const MemoryRegionOps virtio_pci_config_ops = {
    .old_portio = virtio_portio,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void virtio_write_config(PCIDevice *pci_dev, uint32_t address,
                                uint32_t val, int len)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);

    pci_default_write_config(pci_dev, address, val, len);

    if (range_covers_byte(address, len, PCI_COMMAND) &&
        !(pci_dev->config[PCI_COMMAND] & PCI_COMMAND_MASTER) &&
        !(proxy->flags & VIRTIO_PCI_FLAG_BUS_MASTER_BUG)) {
        virtio_pci_stop_ioeventfd(proxy);
        virtio_set_status(proxy->vdev,
                          proxy->vdev->status & ~VIRTIO_CONFIG_S_DRIVER_OK);
    }

    msix_write_config(pci_dev, address, val, len);
}

static unsigned virtio_pci_get_features(void *opaque)
{
    VirtIOPCIProxy *proxy = opaque;
    return proxy->host_features;
}

static void virtio_pci_guest_notifier_read(void *opaque)
{
    VirtQueue *vq = opaque;
    EventNotifier *n = virtio_queue_get_guest_notifier(vq);
    if (event_notifier_test_and_clear(n)) {
        virtio_irq(vq);
    }
}

static int virtio_pci_mask_vq(PCIDevice *dev, unsigned vector,
                              VirtQueue *vq, int masked)
{
    EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);
    int r = kvm_set_irqfd(dev->msix_irq_entries[vector].gsi,
                          event_notifier_get_fd(notifier),
                          !masked);
    if (r < 0) {
        return (r == -ENOSYS) ? 0 : r;
    }
    if (masked) {
        qemu_set_fd_handler(event_notifier_get_fd(notifier),
                            virtio_pci_guest_notifier_read, NULL, vq);
    } else {
        qemu_set_fd_handler(event_notifier_get_fd(notifier),
                            NULL, NULL, NULL);
    }
    return 0;
}

static int virtio_pci_mask_notifier(PCIDevice *dev, unsigned vector,
                                    int masked)
{
    VirtIOPCIProxy *proxy = container_of(dev, VirtIOPCIProxy, pci_dev);
    VirtIODevice *vdev = proxy->vdev;
    int r, n;

    for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
        if (!virtio_queue_get_num(vdev, n)) {
            break;
        }
        if (virtio_queue_vector(vdev, n) != vector) {
            continue;
        }
        r = virtio_pci_mask_vq(dev, vector, virtio_get_queue(vdev, n), masked);
        if (r < 0) {
            goto undo;
        }
    }
    return 0;
undo:
    while (--n >= 0) {
        if (virtio_queue_vector(vdev, n) != vector) {
            continue;
        }
        virtio_pci_mask_vq(dev, vector, virtio_get_queue(vdev, n), !masked);
    }
    return r;
}


static int virtio_pci_set_guest_notifier(void *opaque, int n, bool assign)
{
    VirtIOPCIProxy *proxy = opaque;
    VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
    EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);

    if (assign) {
        int r = event_notifier_init(notifier, 0);
        if (r < 0) {
            return r;
        }
        qemu_set_fd_handler(event_notifier_get_fd(notifier),
                            virtio_pci_guest_notifier_read, NULL, vq);
    } else {
        qemu_set_fd_handler(event_notifier_get_fd(notifier),
                            NULL, NULL, NULL);
        /* Test and clear notifier before closing it,
         * in case poll callback didn't have time to run. */
        virtio_pci_guest_notifier_read(vq);
        event_notifier_cleanup(notifier);
    }

    return 0;
}

static bool virtio_pci_query_guest_notifiers(void *opaque)
{
    VirtIOPCIProxy *proxy = opaque;
    return msix_enabled(&proxy->pci_dev);
}

static int virtio_pci_set_guest_notifiers(void *opaque, bool assign)
{
    VirtIOPCIProxy *proxy = opaque;
    VirtIODevice *vdev = proxy->vdev;
    int r, n;

    /* Must unset mask notifier while guest notifier
     * is still assigned */
    if (kvm_irqchip_in_kernel() && !assign) {
	    r = msix_unset_mask_notifier(&proxy->pci_dev);
            assert(r >= 0);
    }

    for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
        if (!virtio_queue_get_num(vdev, n)) {
            break;
        }

        r = virtio_pci_set_guest_notifier(opaque, n, assign);
        if (r < 0) {
            goto assign_error;
        }
    }

    /* Must set mask notifier after guest notifier
     * has been assigned */
    if (kvm_irqchip_in_kernel() && assign) {
        r = msix_set_mask_notifier(&proxy->pci_dev,
                                   virtio_pci_mask_notifier);
        if (r < 0) {
            goto assign_error;
        }
    }

    return 0;

assign_error:
    /* We get here on assignment failure. Recover by undoing for VQs 0 .. n. */
    while (--n >= 0) {
        virtio_pci_set_guest_notifier(opaque, n, !assign);
    }

    if (!assign) {
        msix_set_mask_notifier(&proxy->pci_dev,
                               virtio_pci_mask_notifier);
    }
    return r;
}

static int virtio_pci_set_host_notifier(void *opaque, int n, bool assign)
{
    VirtIOPCIProxy *proxy = opaque;

    /* Stop using ioeventfd for virtqueue kick if the device starts using host
     * notifiers.  This makes it easy to avoid stepping on each others' toes.
     */
    proxy->ioeventfd_disabled = assign;
    if (assign) {
        virtio_pci_stop_ioeventfd(proxy);
    }
    /* We don't need to start here: it's not needed because backend
     * currently only stops on status change away from ok,
     * reset, vmstop and such. If we do add code to start here,
     * need to check vmstate, device state etc. */
    return virtio_pci_set_host_notifier_internal(proxy, n, assign);
}

static void virtio_pci_vmstate_change(void *opaque, bool running)
{
    VirtIOPCIProxy *proxy = opaque;

    if (running) {
        /* Try to find out if the guest has bus master disabled, but is
           in ready state. Then we have a buggy guest OS. */
        if ((proxy->vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
            !(proxy->pci_dev.config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
            proxy->flags |= VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
        }
        virtio_pci_start_ioeventfd(proxy);
    } else {
        virtio_pci_stop_ioeventfd(proxy);
    }
}

static const VirtIOBindings virtio_pci_bindings = {
    .notify = virtio_pci_notify,
    .save_config = virtio_pci_save_config,
    .load_config = virtio_pci_load_config,
    .save_queue = virtio_pci_save_queue,
    .load_queue = virtio_pci_load_queue,
    .get_features = virtio_pci_get_features,
    .query_guest_notifiers = virtio_pci_query_guest_notifiers,
    .set_host_notifier = virtio_pci_set_host_notifier,
    .set_guest_notifiers = virtio_pci_set_guest_notifiers,
    .vmstate_change = virtio_pci_vmstate_change,
};

void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev)
{
    uint8_t *config;
    uint32_t size;

    proxy->vdev = vdev;

    config = proxy->pci_dev.config;

    if (proxy->class_code) {
        pci_config_set_class(config, proxy->class_code);
    }
    pci_set_word(config + PCI_SUBSYSTEM_VENDOR_ID,
                 pci_get_word(config + PCI_VENDOR_ID));
    pci_set_word(config + PCI_SUBSYSTEM_ID, vdev->device_id);
    config[PCI_INTERRUPT_PIN] = 1;

    memory_region_init(&proxy->msix_bar, "virtio-msix", 4096);
    if (vdev->nvectors && !msix_init(&proxy->pci_dev, vdev->nvectors,
                                     &proxy->msix_bar, 1, 0)) {
        pci_register_bar(&proxy->pci_dev, 1, PCI_BASE_ADDRESS_SPACE_MEMORY,
                         &proxy->msix_bar);
    } else
        vdev->nvectors = 0;

    proxy->pci_dev.config_write = virtio_write_config;

    size = VIRTIO_PCI_REGION_SIZE(&proxy->pci_dev) + vdev->config_len;
    if (size & (size-1))
        size = 1 << qemu_fls(size);

    memory_region_init_io(&proxy->bar, &virtio_pci_config_ops, proxy,
                          "virtio-pci", size);
    pci_register_bar(&proxy->pci_dev, 0, PCI_BASE_ADDRESS_SPACE_IO,
                     &proxy->bar);

    if (!kvm_has_many_ioeventfds()) {
        proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;
    }

    virtio_bind_device(vdev, &virtio_pci_bindings, proxy);
    proxy->host_features |= 0x1 << VIRTIO_F_NOTIFY_ON_EMPTY;
    proxy->host_features |= 0x1 << VIRTIO_F_BAD_FEATURE;
    proxy->host_features = vdev->get_features(vdev, proxy->host_features);
}

static int virtio_blk_init_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
    VirtIODevice *vdev;

    if (proxy->class_code != PCI_CLASS_STORAGE_SCSI &&
        proxy->class_code != PCI_CLASS_STORAGE_OTHER)
        proxy->class_code = PCI_CLASS_STORAGE_SCSI;

    vdev = virtio_blk_init(&pci_dev->qdev, &proxy->blk);
    if (!vdev) {
        return -1;
    }
    vdev->nvectors = proxy->nvectors;
    virtio_init_pci(proxy, vdev);
    /* make the actual value visible */
    proxy->nvectors = vdev->nvectors;
    return 0;
}

static int virtio_exit_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
    int r;

    memory_region_destroy(&proxy->bar);
    r = msix_uninit(pci_dev, &proxy->msix_bar);
    memory_region_destroy(&proxy->msix_bar);
    return r;
}

static int virtio_blk_exit_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);

    virtio_pci_stop_ioeventfd(proxy);
    virtio_blk_exit(proxy->vdev);
    return virtio_exit_pci(pci_dev);
}

static int virtio_serial_init_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
    VirtIODevice *vdev;

    if (proxy->class_code != PCI_CLASS_COMMUNICATION_OTHER &&
        proxy->class_code != PCI_CLASS_DISPLAY_OTHER && /* qemu 0.10 */
        proxy->class_code != PCI_CLASS_OTHERS)          /* qemu-kvm  */
        proxy->class_code = PCI_CLASS_COMMUNICATION_OTHER;

    vdev = virtio_serial_init(&pci_dev->qdev, &proxy->serial);
    if (!vdev) {
        return -1;
    }
    vdev->nvectors = proxy->nvectors == DEV_NVECTORS_UNSPECIFIED
                                        ? proxy->serial.max_virtserial_ports + 1
                                        : proxy->nvectors;
    virtio_init_pci(proxy, vdev);
    proxy->nvectors = vdev->nvectors;
    return 0;
}

static int virtio_serial_exit_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);

    virtio_pci_stop_ioeventfd(proxy);
    virtio_serial_exit(proxy->vdev);
    return virtio_exit_pci(pci_dev);
}

static int virtio_net_init_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
    VirtIODevice *vdev;

    vdev = virtio_net_init(&pci_dev->qdev, &proxy->nic, &proxy->net);

    vdev->nvectors = proxy->nvectors;
    virtio_init_pci(proxy, vdev);

    /* make the actual value visible */
    proxy->nvectors = vdev->nvectors;
    return 0;
}

static int virtio_net_exit_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);

    virtio_pci_stop_ioeventfd(proxy);
    virtio_net_exit(proxy->vdev);
    return virtio_exit_pci(pci_dev);
}

static int virtio_balloon_init_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
    VirtIODevice *vdev;

    if (proxy->class_code != PCI_CLASS_OTHERS &&
        proxy->class_code != PCI_CLASS_MEMORY_RAM) { /* qemu < 1.1 */
        proxy->class_code = PCI_CLASS_OTHERS;
    }

    vdev = virtio_balloon_init(&pci_dev->qdev);
    if (!vdev) {
        return -1;
    }
    virtio_init_pci(proxy, vdev);
    return 0;
}

static int virtio_balloon_exit_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);

    virtio_pci_stop_ioeventfd(proxy);
    virtio_balloon_exit(proxy->vdev);
    return virtio_exit_pci(pci_dev);
}

static Property virtio_blk_properties[] = {
    DEFINE_PROP_HEX32("class", VirtIOPCIProxy, class_code, 0),
    DEFINE_BLOCK_PROPERTIES(VirtIOPCIProxy, blk.conf),
    DEFINE_PROP_STRING("serial", VirtIOPCIProxy, blk.serial),
#ifdef __linux__
    DEFINE_PROP_BIT("scsi", VirtIOPCIProxy, blk.scsi, 0, true),
#endif
    DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true),
    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2),
    DEFINE_VIRTIO_BLK_FEATURES(VirtIOPCIProxy, host_features),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_blk_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = virtio_blk_init_pci;
    k->exit = virtio_blk_exit_pci;
    k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
    k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK;
    k->revision = VIRTIO_PCI_ABI_VERSION;
    k->class_id = PCI_CLASS_STORAGE_SCSI;
    dc->reset = virtio_pci_reset;
    dc->props = virtio_blk_properties;
}

static TypeInfo virtio_blk_info = {
    .name          = "virtio-blk-pci",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(VirtIOPCIProxy),
    .class_init    = virtio_blk_class_init,
};

static Property virtio_net_properties[] = {
    DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, false),
    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3),
    DEFINE_VIRTIO_NET_FEATURES(VirtIOPCIProxy, host_features),
    DEFINE_NIC_PROPERTIES(VirtIOPCIProxy, nic),
    DEFINE_PROP_UINT32("x-txtimer", VirtIOPCIProxy, net.txtimer, TX_TIMER_INTERVAL),
    DEFINE_PROP_INT32("x-txburst", VirtIOPCIProxy, net.txburst, TX_BURST),
    DEFINE_PROP_STRING("tx", VirtIOPCIProxy, net.tx),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_net_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = virtio_net_init_pci;
    k->exit = virtio_net_exit_pci;
    k->romfile = "pxe-virtio.rom";
    k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
    k->device_id = PCI_DEVICE_ID_VIRTIO_NET;
    k->revision = VIRTIO_PCI_ABI_VERSION;
    k->class_id = PCI_CLASS_NETWORK_ETHERNET;
    dc->reset = virtio_pci_reset;
    dc->props = virtio_net_properties;
}

static TypeInfo virtio_net_info = {
    .name          = "virtio-net-pci",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(VirtIOPCIProxy),
    .class_init    = virtio_net_class_init,
};

static Property virtio_serial_properties[] = {
    DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true),
    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, DEV_NVECTORS_UNSPECIFIED),
    DEFINE_PROP_HEX32("class", VirtIOPCIProxy, class_code, 0),
    DEFINE_VIRTIO_COMMON_FEATURES(VirtIOPCIProxy, host_features),
    DEFINE_PROP_UINT32("max_ports", VirtIOPCIProxy, serial.max_virtserial_ports, 31),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_serial_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = virtio_serial_init_pci;
    k->exit = virtio_serial_exit_pci;
    k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
    k->device_id = PCI_DEVICE_ID_VIRTIO_CONSOLE;
    k->revision = VIRTIO_PCI_ABI_VERSION;
    k->class_id = PCI_CLASS_COMMUNICATION_OTHER;
    dc->reset = virtio_pci_reset;
    dc->props = virtio_serial_properties;
}

static TypeInfo virtio_serial_info = {
    .name          = "virtio-serial-pci",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(VirtIOPCIProxy),
    .class_init    = virtio_serial_class_init,
};

static Property virtio_balloon_properties[] = {
    DEFINE_VIRTIO_COMMON_FEATURES(VirtIOPCIProxy, host_features),
    DEFINE_PROP_HEX32("class", VirtIOPCIProxy, class_code, 0),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_balloon_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = virtio_balloon_init_pci;
    k->exit = virtio_balloon_exit_pci;
    k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
    k->device_id = PCI_DEVICE_ID_VIRTIO_BALLOON;
    k->revision = VIRTIO_PCI_ABI_VERSION;
    k->class_id = PCI_CLASS_OTHERS;
    dc->reset = virtio_pci_reset;
    dc->props = virtio_balloon_properties;
}

static TypeInfo virtio_balloon_info = {
    .name          = "virtio-balloon-pci",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(VirtIOPCIProxy),
    .class_init    = virtio_balloon_class_init,
};

static int virtio_scsi_init_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
    VirtIODevice *vdev;

    vdev = virtio_scsi_init(&pci_dev->qdev, &proxy->scsi);
    if (!vdev) {
        return -EINVAL;
    }

    vdev->nvectors = proxy->nvectors;
    virtio_init_pci(proxy, vdev);

    /* make the actual value visible */
    proxy->nvectors = vdev->nvectors;
    return 0;
}

static int virtio_scsi_exit_pci(PCIDevice *pci_dev)
{
    VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);

    virtio_scsi_exit(proxy->vdev);
    return virtio_exit_pci(pci_dev);
}

static Property virtio_scsi_properties[] = {
    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2),
    DEFINE_VIRTIO_SCSI_PROPERTIES(VirtIOPCIProxy, host_features, scsi),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_scsi_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);

    k->init = virtio_scsi_init_pci;
    k->exit = virtio_scsi_exit_pci;
    k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
    k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI;
    k->revision = 0x00;
    k->class_id = PCI_CLASS_STORAGE_SCSI;
    dc->reset = virtio_pci_reset;
    dc->props = virtio_scsi_properties;
}

static TypeInfo virtio_scsi_info = {
    .name          = "virtio-scsi-pci",
    .parent        = TYPE_PCI_DEVICE,
    .instance_size = sizeof(VirtIOPCIProxy),
    .class_init    = virtio_scsi_class_init,
};

static void virtio_pci_register_types(void)
{
    type_register_static(&virtio_blk_info);
    type_register_static(&virtio_net_info);
    type_register_static(&virtio_serial_info);
    type_register_static(&virtio_balloon_info);
    type_register_static(&virtio_scsi_info);
}

type_init(virtio_pci_register_types)