aboutsummaryrefslogtreecommitdiff
path: root/hw/hyperv/hyperv.c
blob: ba94bf9f8db62de04e4889bf4bce9a3c57c42481 (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
/*
 * Hyper-V guest/hypervisor interaction
 *
 * Copyright (c) 2015-2018 Virtuozzo International GmbH.
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "qemu/main-loop.h"
#include "qemu/module.h"
#include "qapi/error.h"
#include "exec/address-spaces.h"
#include "exec/memory.h"
#include "sysemu/kvm.h"
#include "qemu/bitops.h"
#include "qemu/error-report.h"
#include "qemu/lockable.h"
#include "qemu/queue.h"
#include "qemu/rcu.h"
#include "qemu/rcu_queue.h"
#include "hw/hyperv/hyperv.h"
#include "qom/object.h"
#include "target/i386/kvm/hyperv-proto.h"
#include "target/i386/cpu.h"
#include "exec/cpu-all.h"

struct SynICState {
    DeviceState parent_obj;

    CPUState *cs;

    bool sctl_enabled;
    hwaddr msg_page_addr;
    hwaddr event_page_addr;
    MemoryRegion msg_page_mr;
    MemoryRegion event_page_mr;
    struct hyperv_message_page *msg_page;
    struct hyperv_event_flags_page *event_page;

    QemuMutex sint_routes_mutex;
    QLIST_HEAD(, HvSintRoute) sint_routes;
};

#define TYPE_SYNIC "hyperv-synic"
OBJECT_DECLARE_SIMPLE_TYPE(SynICState, SYNIC)

static bool synic_enabled;

bool hyperv_is_synic_enabled(void)
{
    return synic_enabled;
}

static SynICState *get_synic(CPUState *cs)
{
    return SYNIC(object_resolve_path_component(OBJECT(cs), "synic"));
}

static void synic_update(SynICState *synic, bool sctl_enable,
                         hwaddr msg_page_addr, hwaddr event_page_addr)
{

    synic->sctl_enabled = sctl_enable;
    if (synic->msg_page_addr != msg_page_addr) {
        if (synic->msg_page_addr) {
            memory_region_del_subregion(get_system_memory(),
                                        &synic->msg_page_mr);
        }
        if (msg_page_addr) {
            memory_region_add_subregion(get_system_memory(), msg_page_addr,
                                        &synic->msg_page_mr);
        }
        synic->msg_page_addr = msg_page_addr;
    }
    if (synic->event_page_addr != event_page_addr) {
        if (synic->event_page_addr) {
            memory_region_del_subregion(get_system_memory(),
                                        &synic->event_page_mr);
        }
        if (event_page_addr) {
            memory_region_add_subregion(get_system_memory(), event_page_addr,
                                        &synic->event_page_mr);
        }
        synic->event_page_addr = event_page_addr;
    }
}

void hyperv_synic_update(CPUState *cs, bool sctl_enable,
                         hwaddr msg_page_addr, hwaddr event_page_addr)
{
    SynICState *synic = get_synic(cs);

    if (!synic) {
        return;
    }

    synic_update(synic, sctl_enable, msg_page_addr, event_page_addr);
}

static void synic_realize(DeviceState *dev, Error **errp)
{
    Object *obj = OBJECT(dev);
    SynICState *synic = SYNIC(dev);
    char *msgp_name, *eventp_name;
    uint32_t vp_index;

    /* memory region names have to be globally unique */
    vp_index = hyperv_vp_index(synic->cs);
    msgp_name = g_strdup_printf("synic-%u-msg-page", vp_index);
    eventp_name = g_strdup_printf("synic-%u-event-page", vp_index);

    memory_region_init_ram(&synic->msg_page_mr, obj, msgp_name,
                           sizeof(*synic->msg_page), &error_abort);
    memory_region_init_ram(&synic->event_page_mr, obj, eventp_name,
                           sizeof(*synic->event_page), &error_abort);
    synic->msg_page = memory_region_get_ram_ptr(&synic->msg_page_mr);
    synic->event_page = memory_region_get_ram_ptr(&synic->event_page_mr);
    qemu_mutex_init(&synic->sint_routes_mutex);
    QLIST_INIT(&synic->sint_routes);

    g_free(msgp_name);
    g_free(eventp_name);
}

static void synic_reset(DeviceState *dev)
{
    SynICState *synic = SYNIC(dev);
    memset(synic->msg_page, 0, sizeof(*synic->msg_page));
    memset(synic->event_page, 0, sizeof(*synic->event_page));
    synic_update(synic, false, 0, 0);
    assert(QLIST_EMPTY(&synic->sint_routes));
}

static void synic_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->realize = synic_realize;
    device_class_set_legacy_reset(dc, synic_reset);
    dc->user_creatable = false;
}

void hyperv_synic_add(CPUState *cs)
{
    Object *obj;
    SynICState *synic;

    obj = object_new(TYPE_SYNIC);
    synic = SYNIC(obj);
    synic->cs = cs;
    object_property_add_child(OBJECT(cs), "synic", obj);
    object_unref(obj);
    qdev_realize(DEVICE(obj), NULL, &error_abort);
    synic_enabled = true;
}

void hyperv_synic_reset(CPUState *cs)
{
    SynICState *synic = get_synic(cs);

    if (synic) {
        device_cold_reset(DEVICE(synic));
    }
}

static const TypeInfo synic_type_info = {
    .name = TYPE_SYNIC,
    .parent = TYPE_DEVICE,
    .instance_size = sizeof(SynICState),
    .class_init = synic_class_init,
};

static void synic_register_types(void)
{
    type_register_static(&synic_type_info);
}

type_init(synic_register_types)

/*
 * KVM has its own message producers (SynIC timers).  To guarantee
 * serialization with both KVM vcpu and the guest cpu, the messages are first
 * staged in an intermediate area and then posted to the SynIC message page in
 * the vcpu thread.
 */
typedef struct HvSintStagedMessage {
    /* message content staged by hyperv_post_msg */
    struct hyperv_message msg;
    /* callback + data (r/o) to complete the processing in a BH */
    HvSintMsgCb cb;
    void *cb_data;
    /* message posting status filled by cpu_post_msg */
    int status;
    /* passing the buck: */
    enum {
        /* initial state */
        HV_STAGED_MSG_FREE,
        /*
         * hyperv_post_msg (e.g. in main loop) grabs the staged area (FREE ->
         * BUSY), copies msg, and schedules cpu_post_msg on the assigned cpu
         */
        HV_STAGED_MSG_BUSY,
        /*
         * cpu_post_msg (vcpu thread) tries to copy staged msg to msg slot,
         * notify the guest, records the status, marks the posting done (BUSY
         * -> POSTED), and schedules sint_msg_bh BH
         */
        HV_STAGED_MSG_POSTED,
        /*
         * sint_msg_bh (BH) verifies that the posting is done, runs the
         * callback, and starts over (POSTED -> FREE)
         */
    } state;
} HvSintStagedMessage;

struct HvSintRoute {
    uint32_t sint;
    SynICState *synic;
    int gsi;
    EventNotifier sint_set_notifier;
    EventNotifier sint_ack_notifier;

    HvSintStagedMessage *staged_msg;

    unsigned refcount;
    QLIST_ENTRY(HvSintRoute) link;
};

static CPUState *hyperv_find_vcpu(uint32_t vp_index)
{
    CPUState *cs = qemu_get_cpu(vp_index);
    assert(hyperv_vp_index(cs) == vp_index);
    return cs;
}

/*
 * BH to complete the processing of a staged message.
 */
static void sint_msg_bh(void *opaque)
{
    HvSintRoute *sint_route = opaque;
    HvSintStagedMessage *staged_msg = sint_route->staged_msg;

    if (qatomic_read(&staged_msg->state) != HV_STAGED_MSG_POSTED) {
        /* status nor ready yet (spurious ack from guest?), ignore */
        return;
    }

    staged_msg->cb(staged_msg->cb_data, staged_msg->status);
    staged_msg->status = 0;

    /* staged message processing finished, ready to start over */
    qatomic_set(&staged_msg->state, HV_STAGED_MSG_FREE);
    /* drop the reference taken in hyperv_post_msg */
    hyperv_sint_route_unref(sint_route);
}

/*
 * Worker to transfer the message from the staging area into the SynIC message
 * page in vcpu context.
 */
static void cpu_post_msg(CPUState *cs, run_on_cpu_data data)
{
    HvSintRoute *sint_route = data.host_ptr;
    HvSintStagedMessage *staged_msg = sint_route->staged_msg;
    SynICState *synic = sint_route->synic;
    struct hyperv_message *dst_msg;
    bool wait_for_sint_ack = false;

    assert(staged_msg->state == HV_STAGED_MSG_BUSY);

    if (!synic->msg_page_addr) {
        staged_msg->status = -ENXIO;
        goto posted;
    }

    dst_msg = &synic->msg_page->slot[sint_route->sint];

    if (dst_msg->header.message_type != HV_MESSAGE_NONE) {
        dst_msg->header.message_flags |= HV_MESSAGE_FLAG_PENDING;
        staged_msg->status = -EAGAIN;
        wait_for_sint_ack = true;
    } else {
        memcpy(dst_msg, &staged_msg->msg, sizeof(*dst_msg));
        staged_msg->status = hyperv_sint_route_set_sint(sint_route);
    }

    memory_region_set_dirty(&synic->msg_page_mr, 0, sizeof(*synic->msg_page));

posted:
    qatomic_set(&staged_msg->state, HV_STAGED_MSG_POSTED);
    /*
     * Notify the msg originator of the progress made; if the slot was busy we
     * set msg_pending flag in it so it will be the guest who will do EOM and
     * trigger the notification from KVM via sint_ack_notifier
     */
    if (!wait_for_sint_ack) {
        aio_bh_schedule_oneshot(qemu_get_aio_context(), sint_msg_bh,
                                sint_route);
    }
}

/*
 * Post a Hyper-V message to the staging area, for delivery to guest in the
 * vcpu thread.
 */
int hyperv_post_msg(HvSintRoute *sint_route, struct hyperv_message *src_msg)
{
    HvSintStagedMessage *staged_msg = sint_route->staged_msg;

    assert(staged_msg);

    /* grab the staging area */
    if (qatomic_cmpxchg(&staged_msg->state, HV_STAGED_MSG_FREE,
                       HV_STAGED_MSG_BUSY) != HV_STAGED_MSG_FREE) {
        return -EAGAIN;
    }

    memcpy(&staged_msg->msg, src_msg, sizeof(*src_msg));

    /* hold a reference on sint_route until the callback is finished */
    hyperv_sint_route_ref(sint_route);

    /* schedule message posting attempt in vcpu thread */
    async_run_on_cpu(sint_route->synic->cs, cpu_post_msg,
                     RUN_ON_CPU_HOST_PTR(sint_route));
    return 0;
}

static void sint_ack_handler(EventNotifier *notifier)
{
    HvSintRoute *sint_route = container_of(notifier, HvSintRoute,
                                           sint_ack_notifier);
    event_notifier_test_and_clear(notifier);

    /*
     * the guest consumed the previous message so complete the current one with
     * -EAGAIN and let the msg originator retry
     */
    aio_bh_schedule_oneshot(qemu_get_aio_context(), sint_msg_bh, sint_route);
}

/*
 * Set given event flag for a given sint on a given vcpu, and signal the sint.
 */
int hyperv_set_event_flag(HvSintRoute *sint_route, unsigned eventno)
{
    int ret;
    SynICState *synic = sint_route->synic;
    unsigned long *flags, set_mask;
    unsigned set_idx;

    if (eventno > HV_EVENT_FLAGS_COUNT) {
        return -EINVAL;
    }
    if (!synic->sctl_enabled || !synic->event_page_addr) {
        return -ENXIO;
    }

    set_idx = BIT_WORD(eventno);
    set_mask = BIT_MASK(eventno);
    flags = synic->event_page->slot[sint_route->sint].flags;

    if ((qatomic_fetch_or(&flags[set_idx], set_mask) & set_mask) != set_mask) {
        memory_region_set_dirty(&synic->event_page_mr, 0,
                                sizeof(*synic->event_page));
        ret = hyperv_sint_route_set_sint(sint_route);
    } else {
        ret = 0;
    }
    return ret;
}

static int kvm_irqchip_add_hv_sint_route(KVMState *s, uint32_t vcpu, uint32_t sint)
{
    struct kvm_irq_routing_entry kroute = {};
    int virq;

    if (!kvm_gsi_routing_enabled()) {
        return -ENOSYS;
    }
    virq = kvm_irqchip_get_virq(s);
    if (virq < 0) {
        return virq;
    }

    kroute.gsi = virq;
    kroute.type = KVM_IRQ_ROUTING_HV_SINT;
    kroute.flags = 0;
    kroute.u.hv_sint.vcpu = vcpu;
    kroute.u.hv_sint.sint = sint;

    kvm_add_routing_entry(s, &kroute);
    kvm_irqchip_commit_routes(s);

    return virq;
}

HvSintRoute *hyperv_sint_route_new(uint32_t vp_index, uint32_t sint,
                                   HvSintMsgCb cb, void *cb_data)
{
    HvSintRoute *sint_route = NULL;
    EventNotifier *ack_notifier = NULL;
    int r, gsi;
    CPUState *cs;
    SynICState *synic;
    bool ack_event_initialized = false;

    cs = hyperv_find_vcpu(vp_index);
    if (!cs) {
        return NULL;
    }

    synic = get_synic(cs);
    if (!synic) {
        return NULL;
    }

    sint_route = g_new0(HvSintRoute, 1);
    if (!sint_route) {
        return NULL;
    }

    sint_route->synic = synic;
    sint_route->sint = sint;
    sint_route->refcount = 1;

    ack_notifier = cb ? &sint_route->sint_ack_notifier : NULL;
    if (ack_notifier) {
        sint_route->staged_msg = g_new0(HvSintStagedMessage, 1);
        if (!sint_route->staged_msg) {
            goto cleanup_err_sint;
        }
        sint_route->staged_msg->cb = cb;
        sint_route->staged_msg->cb_data = cb_data;

        r = event_notifier_init(ack_notifier, false);
        if (r) {
            goto cleanup_err_sint;
        }
        event_notifier_set_handler(ack_notifier, sint_ack_handler);
        ack_event_initialized = true;
    }

    /* See if we are done or we need to setup a GSI for this SintRoute */
    if (!synic->sctl_enabled) {
        goto cleanup;
    }

    /* We need to setup a GSI for this SintRoute */
    r = event_notifier_init(&sint_route->sint_set_notifier, false);
    if (r) {
        goto cleanup_err_sint;
    }

    gsi = kvm_irqchip_add_hv_sint_route(kvm_state, vp_index, sint);
    if (gsi < 0) {
        goto cleanup_err_sint_notifier;
    }

    r = kvm_irqchip_add_irqfd_notifier_gsi(kvm_state,
                                           &sint_route->sint_set_notifier,
                                           ack_notifier, gsi);
    if (r) {
        goto cleanup_err_irqfd;
    }
    sint_route->gsi = gsi;
cleanup:
    qemu_mutex_lock(&synic->sint_routes_mutex);
    QLIST_INSERT_HEAD(&synic->sint_routes, sint_route, link);
    qemu_mutex_unlock(&synic->sint_routes_mutex);
    return sint_route;

cleanup_err_irqfd:
    kvm_irqchip_release_virq(kvm_state, gsi);

cleanup_err_sint_notifier:
    event_notifier_cleanup(&sint_route->sint_set_notifier);

cleanup_err_sint:
    if (ack_notifier) {
        if (ack_event_initialized) {
            event_notifier_set_handler(ack_notifier, NULL);
            event_notifier_cleanup(ack_notifier);
        }

        g_free(sint_route->staged_msg);
    }

    g_free(sint_route);
    return NULL;
}

void hyperv_sint_route_ref(HvSintRoute *sint_route)
{
    sint_route->refcount++;
}

void hyperv_sint_route_unref(HvSintRoute *sint_route)
{
    SynICState *synic;

    if (!sint_route) {
        return;
    }

    assert(sint_route->refcount > 0);

    if (--sint_route->refcount) {
        return;
    }

    synic = sint_route->synic;
    qemu_mutex_lock(&synic->sint_routes_mutex);
    QLIST_REMOVE(sint_route, link);
    qemu_mutex_unlock(&synic->sint_routes_mutex);

    if (sint_route->gsi) {
        kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state,
                                              &sint_route->sint_set_notifier,
                                              sint_route->gsi);
        kvm_irqchip_release_virq(kvm_state, sint_route->gsi);
        event_notifier_cleanup(&sint_route->sint_set_notifier);
    }

    if (sint_route->staged_msg) {
        event_notifier_set_handler(&sint_route->sint_ack_notifier, NULL);
        event_notifier_cleanup(&sint_route->sint_ack_notifier);
        g_free(sint_route->staged_msg);
    }
    g_free(sint_route);
}

int hyperv_sint_route_set_sint(HvSintRoute *sint_route)
{
    if (!sint_route->gsi) {
        return 0;
    }

    return event_notifier_set(&sint_route->sint_set_notifier);
}

typedef struct MsgHandler {
    struct rcu_head rcu;
    QLIST_ENTRY(MsgHandler) link;
    uint32_t conn_id;
    HvMsgHandler handler;
    void *data;
} MsgHandler;

typedef struct EventFlagHandler {
    struct rcu_head rcu;
    QLIST_ENTRY(EventFlagHandler) link;
    uint32_t conn_id;
    EventNotifier *notifier;
} EventFlagHandler;

static QLIST_HEAD(, MsgHandler) msg_handlers;
static QLIST_HEAD(, EventFlagHandler) event_flag_handlers;
static QemuMutex handlers_mutex;

static void __attribute__((constructor)) hv_init(void)
{
    QLIST_INIT(&msg_handlers);
    QLIST_INIT(&event_flag_handlers);
    qemu_mutex_init(&handlers_mutex);
}

int hyperv_set_msg_handler(uint32_t conn_id, HvMsgHandler handler, void *data)
{
    int ret;
    MsgHandler *mh;

    QEMU_LOCK_GUARD(&handlers_mutex);
    QLIST_FOREACH(mh, &msg_handlers, link) {
        if (mh->conn_id == conn_id) {
            if (handler) {
                ret = -EEXIST;
            } else {
                QLIST_REMOVE_RCU(mh, link);
                g_free_rcu(mh, rcu);
                ret = 0;
            }
            return ret;
        }
    }

    if (handler) {
        mh = g_new(MsgHandler, 1);
        mh->conn_id = conn_id;
        mh->handler = handler;
        mh->data = data;
        QLIST_INSERT_HEAD_RCU(&msg_handlers, mh, link);
        ret = 0;
    } else {
        ret = -ENOENT;
    }

    return ret;
}

uint16_t hyperv_hcall_post_message(uint64_t param, bool fast)
{
    uint16_t ret;
    hwaddr len;
    struct hyperv_post_message_input *msg;
    MsgHandler *mh;

    if (fast) {
        return HV_STATUS_INVALID_HYPERCALL_CODE;
    }
    if (param & (__alignof__(*msg) - 1)) {
        return HV_STATUS_INVALID_ALIGNMENT;
    }

    len = sizeof(*msg);
    msg = cpu_physical_memory_map(param, &len, 0);
    if (len < sizeof(*msg)) {
        ret = HV_STATUS_INSUFFICIENT_MEMORY;
        goto unmap;
    }
    if (msg->payload_size > sizeof(msg->payload)) {
        ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
        goto unmap;
    }

    ret = HV_STATUS_INVALID_CONNECTION_ID;
    WITH_RCU_READ_LOCK_GUARD() {
        QLIST_FOREACH_RCU(mh, &msg_handlers, link) {
            if (mh->conn_id == (msg->connection_id & HV_CONNECTION_ID_MASK)) {
                ret = mh->handler(msg, mh->data);
                break;
            }
        }
    }

unmap:
    cpu_physical_memory_unmap(msg, len, 0, 0);
    return ret;
}

static int set_event_flag_handler(uint32_t conn_id, EventNotifier *notifier)
{
    int ret;
    EventFlagHandler *handler;

    QEMU_LOCK_GUARD(&handlers_mutex);
    QLIST_FOREACH(handler, &event_flag_handlers, link) {
        if (handler->conn_id == conn_id) {
            if (notifier) {
                ret = -EEXIST;
            } else {
                QLIST_REMOVE_RCU(handler, link);
                g_free_rcu(handler, rcu);
                ret = 0;
            }
            return ret;
        }
    }

    if (notifier) {
        handler = g_new(EventFlagHandler, 1);
        handler->conn_id = conn_id;
        handler->notifier = notifier;
        QLIST_INSERT_HEAD_RCU(&event_flag_handlers, handler, link);
        ret = 0;
    } else {
        ret = -ENOENT;
    }

    return ret;
}

static bool process_event_flags_userspace;

int hyperv_set_event_flag_handler(uint32_t conn_id, EventNotifier *notifier)
{
    if (!process_event_flags_userspace &&
        !kvm_check_extension(kvm_state, KVM_CAP_HYPERV_EVENTFD)) {
        process_event_flags_userspace = true;

        warn_report("Hyper-V event signaling is not supported by this kernel; "
                    "using slower userspace hypercall processing");
    }

    if (!process_event_flags_userspace) {
        struct kvm_hyperv_eventfd hvevfd = {
            .conn_id = conn_id,
            .fd = notifier ? event_notifier_get_fd(notifier) : -1,
            .flags = notifier ? 0 : KVM_HYPERV_EVENTFD_DEASSIGN,
        };

        return kvm_vm_ioctl(kvm_state, KVM_HYPERV_EVENTFD, &hvevfd);
    }
    return set_event_flag_handler(conn_id, notifier);
}

uint16_t hyperv_hcall_signal_event(uint64_t param, bool fast)
{
    EventFlagHandler *handler;

    if (unlikely(!fast)) {
        hwaddr addr = param;

        if (addr & (__alignof__(addr) - 1)) {
            return HV_STATUS_INVALID_ALIGNMENT;
        }

        param = ldq_phys(&address_space_memory, addr);
    }

    /*
     * Per spec, bits 32-47 contain the extra "flag number".  However, we
     * have no use for it, and in all known usecases it is zero, so just
     * report lookup failure if it isn't.
     */
    if (param & 0xffff00000000ULL) {
        return HV_STATUS_INVALID_PORT_ID;
    }
    /* remaining bits are reserved-zero */
    if (param & ~HV_CONNECTION_ID_MASK) {
        return HV_STATUS_INVALID_HYPERCALL_INPUT;
    }

    RCU_READ_LOCK_GUARD();
    QLIST_FOREACH_RCU(handler, &event_flag_handlers, link) {
        if (handler->conn_id == param) {
            event_notifier_set(handler->notifier);
            return 0;
        }
    }
    return HV_STATUS_INVALID_CONNECTION_ID;
}

static HvSynDbgHandler hv_syndbg_handler;
static void *hv_syndbg_context;

void hyperv_set_syndbg_handler(HvSynDbgHandler handler, void *context)
{
    assert(!hv_syndbg_handler);
    hv_syndbg_handler = handler;
    hv_syndbg_context = context;
}

uint16_t hyperv_hcall_reset_dbg_session(uint64_t outgpa)
{
    uint16_t ret;
    HvSynDbgMsg msg;
    struct hyperv_reset_debug_session_output *reset_dbg_session = NULL;
    hwaddr len;

    if (!hv_syndbg_handler) {
        ret = HV_STATUS_INVALID_HYPERCALL_CODE;
        goto cleanup;
    }

    len = sizeof(*reset_dbg_session);
    reset_dbg_session = cpu_physical_memory_map(outgpa, &len, 1);
    if (!reset_dbg_session || len < sizeof(*reset_dbg_session)) {
        ret = HV_STATUS_INSUFFICIENT_MEMORY;
        goto cleanup;
    }

    msg.type = HV_SYNDBG_MSG_CONNECTION_INFO;
    ret = hv_syndbg_handler(hv_syndbg_context, &msg);
    if (ret) {
        goto cleanup;
    }

    reset_dbg_session->host_ip = msg.u.connection_info.host_ip;
    reset_dbg_session->host_port = msg.u.connection_info.host_port;
    /* The following fields are only used as validation for KDVM */
    memset(&reset_dbg_session->host_mac, 0,
           sizeof(reset_dbg_session->host_mac));
    reset_dbg_session->target_ip = msg.u.connection_info.host_ip;
    reset_dbg_session->target_port = msg.u.connection_info.host_port;
    memset(&reset_dbg_session->target_mac, 0,
           sizeof(reset_dbg_session->target_mac));
cleanup:
    if (reset_dbg_session) {
        cpu_physical_memory_unmap(reset_dbg_session,
                                  sizeof(*reset_dbg_session), 1, len);
    }

    return ret;
}

uint16_t hyperv_hcall_retreive_dbg_data(uint64_t ingpa, uint64_t outgpa,
                                        bool fast)
{
    uint16_t ret;
    struct hyperv_retrieve_debug_data_input *debug_data_in = NULL;
    struct hyperv_retrieve_debug_data_output *debug_data_out = NULL;
    hwaddr in_len, out_len;
    HvSynDbgMsg msg;

    if (fast || !hv_syndbg_handler) {
        ret = HV_STATUS_INVALID_HYPERCALL_CODE;
        goto cleanup;
    }

    in_len = sizeof(*debug_data_in);
    debug_data_in = cpu_physical_memory_map(ingpa, &in_len, 0);
    if (!debug_data_in || in_len < sizeof(*debug_data_in)) {
        ret = HV_STATUS_INSUFFICIENT_MEMORY;
        goto cleanup;
    }

    out_len = sizeof(*debug_data_out);
    debug_data_out = cpu_physical_memory_map(outgpa, &out_len, 1);
    if (!debug_data_out || out_len < sizeof(*debug_data_out)) {
        ret = HV_STATUS_INSUFFICIENT_MEMORY;
        goto cleanup;
    }

    msg.type = HV_SYNDBG_MSG_RECV;
    msg.u.recv.buf_gpa = outgpa + sizeof(*debug_data_out);
    msg.u.recv.count = TARGET_PAGE_SIZE - sizeof(*debug_data_out);
    msg.u.recv.options = debug_data_in->options;
    msg.u.recv.timeout = debug_data_in->timeout;
    msg.u.recv.is_raw = true;
    ret = hv_syndbg_handler(hv_syndbg_context, &msg);
    if (ret == HV_STATUS_NO_DATA) {
        debug_data_out->retrieved_count = 0;
        debug_data_out->remaining_count = debug_data_in->count;
        goto cleanup;
    } else if (ret != HV_STATUS_SUCCESS) {
        goto cleanup;
    }

    debug_data_out->retrieved_count = msg.u.recv.retrieved_count;
    debug_data_out->remaining_count =
        debug_data_in->count - msg.u.recv.retrieved_count;
cleanup:
    if (debug_data_out) {
        cpu_physical_memory_unmap(debug_data_out, sizeof(*debug_data_out), 1,
                                  out_len);
    }

    if (debug_data_in) {
        cpu_physical_memory_unmap(debug_data_in, sizeof(*debug_data_in), 0,
                                  in_len);
    }

    return ret;
}

uint16_t hyperv_hcall_post_dbg_data(uint64_t ingpa, uint64_t outgpa, bool fast)
{
    uint16_t ret;
    struct hyperv_post_debug_data_input *post_data_in = NULL;
    struct hyperv_post_debug_data_output *post_data_out = NULL;
    hwaddr in_len, out_len;
    HvSynDbgMsg msg;

    if (fast || !hv_syndbg_handler) {
        ret = HV_STATUS_INVALID_HYPERCALL_CODE;
        goto cleanup;
    }

    in_len = sizeof(*post_data_in);
    post_data_in = cpu_physical_memory_map(ingpa, &in_len, 0);
    if (!post_data_in || in_len < sizeof(*post_data_in)) {
        ret = HV_STATUS_INSUFFICIENT_MEMORY;
        goto cleanup;
    }

    if (post_data_in->count > TARGET_PAGE_SIZE - sizeof(*post_data_in)) {
        ret = HV_STATUS_INVALID_PARAMETER;
        goto cleanup;
    }

    out_len = sizeof(*post_data_out);
    post_data_out = cpu_physical_memory_map(outgpa, &out_len, 1);
    if (!post_data_out || out_len < sizeof(*post_data_out)) {
        ret = HV_STATUS_INSUFFICIENT_MEMORY;
        goto cleanup;
    }

    msg.type = HV_SYNDBG_MSG_SEND;
    msg.u.send.buf_gpa = ingpa + sizeof(*post_data_in);
    msg.u.send.count = post_data_in->count;
    msg.u.send.is_raw = true;
    ret = hv_syndbg_handler(hv_syndbg_context, &msg);
    if (ret != HV_STATUS_SUCCESS) {
        goto cleanup;
    }

    post_data_out->pending_count = msg.u.send.pending_count;
    ret = post_data_out->pending_count ? HV_STATUS_INSUFFICIENT_BUFFERS :
                                         HV_STATUS_SUCCESS;
cleanup:
    if (post_data_out) {
        cpu_physical_memory_unmap(post_data_out,
                                  sizeof(*post_data_out), 1, out_len);
    }

    if (post_data_in) {
        cpu_physical_memory_unmap(post_data_in,
                                  sizeof(*post_data_in), 0, in_len);
    }

    return ret;
}

uint32_t hyperv_syndbg_send(uint64_t ingpa, uint32_t count)
{
    HvSynDbgMsg msg;

    if (!hv_syndbg_handler) {
        return HV_SYNDBG_STATUS_INVALID;
    }

    msg.type = HV_SYNDBG_MSG_SEND;
    msg.u.send.buf_gpa = ingpa;
    msg.u.send.count = count;
    msg.u.send.is_raw = false;
    if (hv_syndbg_handler(hv_syndbg_context, &msg)) {
        return HV_SYNDBG_STATUS_INVALID;
    }

    return HV_SYNDBG_STATUS_SEND_SUCCESS;
}

uint32_t hyperv_syndbg_recv(uint64_t ingpa, uint32_t count)
{
    uint16_t ret;
    HvSynDbgMsg msg;

    if (!hv_syndbg_handler) {
        return HV_SYNDBG_STATUS_INVALID;
    }

    msg.type = HV_SYNDBG_MSG_RECV;
    msg.u.recv.buf_gpa = ingpa;
    msg.u.recv.count = count;
    msg.u.recv.options = 0;
    msg.u.recv.timeout = 0;
    msg.u.recv.is_raw = false;
    ret = hv_syndbg_handler(hv_syndbg_context, &msg);
    if (ret != HV_STATUS_SUCCESS) {
        return 0;
    }

    return HV_SYNDBG_STATUS_SET_SIZE(HV_SYNDBG_STATUS_RECV_SUCCESS,
                                     msg.u.recv.retrieved_count);
}

void hyperv_syndbg_set_pending_page(uint64_t ingpa)
{
    HvSynDbgMsg msg;

    if (!hv_syndbg_handler) {
        return;
    }

    msg.type = HV_SYNDBG_MSG_SET_PENDING_PAGE;
    msg.u.pending_page.buf_gpa = ingpa;
    hv_syndbg_handler(hv_syndbg_context, &msg);
}

uint64_t hyperv_syndbg_query_options(void)
{
    HvSynDbgMsg msg;

    if (!hv_syndbg_handler) {
        return 0;
    }

    msg.type = HV_SYNDBG_MSG_QUERY_OPTIONS;
    if (hv_syndbg_handler(hv_syndbg_context, &msg) != HV_STATUS_SUCCESS) {
        return 0;
    }

    return msg.u.query_options.options;
}

static bool vmbus_recommended_features_enabled;

bool hyperv_are_vmbus_recommended_features_enabled(void)
{
    return vmbus_recommended_features_enabled;
}

void hyperv_set_vmbus_recommended_features_enabled(void)
{
    vmbus_recommended_features_enabled = true;
}