aboutsummaryrefslogtreecommitdiff
path: root/block/blkio.c
blob: 82f26eedd29bbd63875bea2661115d90d7049753 (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
/* SPDX-License-Identifier: LGPL-2.1-or-later */
/*
 * libblkio BlockDriver
 *
 * Copyright Red Hat, Inc.
 *
 * Author:
 *   Stefan Hajnoczi <stefanha@redhat.com>
 */

#include "qemu/osdep.h"
#include <blkio.h>
#include "block/block_int.h"
#include "exec/memory.h"
#include "exec/cpu-common.h" /* for qemu_ram_get_fd() */
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qapi/qmp/qdict.h"
#include "qemu/module.h"
#include "exec/memory.h" /* for ram_block_discard_disable() */

/*
 * Keep the QEMU BlockDriver names identical to the libblkio driver names.
 * Using macros instead of typing out the string literals avoids typos.
 */
#define DRIVER_IO_URING "io_uring"
#define DRIVER_NVME_IO_URING "nvme-io_uring"
#define DRIVER_VIRTIO_BLK_VHOST_USER "virtio-blk-vhost-user"
#define DRIVER_VIRTIO_BLK_VHOST_VDPA "virtio-blk-vhost-vdpa"

/*
 * Allocated bounce buffers are kept in a list sorted by buffer address.
 */
typedef struct BlkioBounceBuf {
    QLIST_ENTRY(BlkioBounceBuf) next;

    /* The bounce buffer */
    struct iovec buf;
} BlkioBounceBuf;

typedef struct {
    /*
     * libblkio is not thread-safe so this lock protects ->blkio and
     * ->blkioq.
     */
    QemuMutex blkio_lock;
    struct blkio *blkio;
    struct blkioq *blkioq; /* make this multi-queue in the future... */
    int completion_fd;

    /*
     * Polling fetches the next completion into this field.
     *
     * No lock is necessary since only one thread calls aio_poll() and invokes
     * fd and poll handlers.
     */
    struct blkio_completion poll_completion;

    /*
     * Protects ->bounce_pool, ->bounce_bufs, ->bounce_available.
     *
     * Lock ordering: ->bounce_lock before ->blkio_lock.
     */
    CoMutex bounce_lock;

    /* Bounce buffer pool */
    struct blkio_mem_region bounce_pool;

    /* Sorted list of allocated bounce buffers */
    QLIST_HEAD(, BlkioBounceBuf) bounce_bufs;

    /* Queue for coroutines waiting for bounce buffer space */
    CoQueue bounce_available;

    /* The value of the "mem-region-alignment" property */
    size_t mem_region_alignment;

    /* Can we skip adding/deleting blkio_mem_regions? */
    bool needs_mem_regions;

    /* Are file descriptors necessary for blkio_mem_regions? */
    bool needs_mem_region_fd;

    /* Are madvise(MADV_DONTNEED)-style operations unavailable? */
    bool may_pin_mem_regions;
} BDRVBlkioState;

/* Called with s->bounce_lock held */
static int blkio_resize_bounce_pool(BDRVBlkioState *s, int64_t bytes)
{
    /* There can be no allocated bounce buffers during resize */
    assert(QLIST_EMPTY(&s->bounce_bufs));

    /* Pad size to reduce frequency of resize calls */
    bytes += 128 * 1024;

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        int ret;

        if (s->bounce_pool.addr) {
            blkio_unmap_mem_region(s->blkio, &s->bounce_pool);
            blkio_free_mem_region(s->blkio, &s->bounce_pool);
            memset(&s->bounce_pool, 0, sizeof(s->bounce_pool));
        }

        /* Automatically freed when s->blkio is destroyed */
        ret = blkio_alloc_mem_region(s->blkio, &s->bounce_pool, bytes);
        if (ret < 0) {
            return ret;
        }

        ret = blkio_map_mem_region(s->blkio, &s->bounce_pool);
        if (ret < 0) {
            blkio_free_mem_region(s->blkio, &s->bounce_pool);
            memset(&s->bounce_pool, 0, sizeof(s->bounce_pool));
            return ret;
        }
    }

    return 0;
}

/* Called with s->bounce_lock held */
static bool
blkio_do_alloc_bounce_buffer(BDRVBlkioState *s, BlkioBounceBuf *bounce,
                             int64_t bytes)
{
    void *addr = s->bounce_pool.addr;
    BlkioBounceBuf *cur = NULL;
    BlkioBounceBuf *prev = NULL;
    ptrdiff_t space;

    /*
     * This is just a linear search over the holes between requests. An
     * efficient allocator would be nice.
     */
    QLIST_FOREACH(cur, &s->bounce_bufs, next) {
        space = cur->buf.iov_base - addr;
        if (bytes <= space) {
            QLIST_INSERT_BEFORE(cur, bounce, next);
            bounce->buf.iov_base = addr;
            bounce->buf.iov_len = bytes;
            return true;
        }

        addr = cur->buf.iov_base + cur->buf.iov_len;
        prev = cur;
    }

    /* Is there space after the last request? */
    space = s->bounce_pool.addr + s->bounce_pool.len - addr;
    if (bytes > space) {
        return false;
    }
    if (prev) {
        QLIST_INSERT_AFTER(prev, bounce, next);
    } else {
        QLIST_INSERT_HEAD(&s->bounce_bufs, bounce, next);
    }
    bounce->buf.iov_base = addr;
    bounce->buf.iov_len = bytes;
    return true;
}

static int coroutine_fn
blkio_alloc_bounce_buffer(BDRVBlkioState *s, BlkioBounceBuf *bounce,
                          int64_t bytes)
{
    /*
     * Ensure fairness: first time around we join the back of the queue,
     * subsequently we join the front so we don't lose our place.
     */
    CoQueueWaitFlags wait_flags = 0;

    QEMU_LOCK_GUARD(&s->bounce_lock);

    /* Ensure fairness: don't even try if other requests are already waiting */
    if (!qemu_co_queue_empty(&s->bounce_available)) {
        qemu_co_queue_wait_flags(&s->bounce_available, &s->bounce_lock,
                                 wait_flags);
        wait_flags = CO_QUEUE_WAIT_FRONT;
    }

    while (true) {
        if (blkio_do_alloc_bounce_buffer(s, bounce, bytes)) {
            /* Kick the next queued request since there may be space */
            qemu_co_queue_next(&s->bounce_available);
            return 0;
        }

        /*
         * If there are no in-flight requests then the pool was simply too
         * small.
         */
        if (QLIST_EMPTY(&s->bounce_bufs)) {
            bool ok;
            int ret;

            ret = blkio_resize_bounce_pool(s, bytes);
            if (ret < 0) {
                /* Kick the next queued request since that may fail too */
                qemu_co_queue_next(&s->bounce_available);
                return ret;
            }

            ok = blkio_do_alloc_bounce_buffer(s, bounce, bytes);
            assert(ok); /* must have space this time */
            return 0;
        }

        qemu_co_queue_wait_flags(&s->bounce_available, &s->bounce_lock,
                                 wait_flags);
        wait_flags = CO_QUEUE_WAIT_FRONT;
    }
}

static void coroutine_fn blkio_free_bounce_buffer(BDRVBlkioState *s,
                                                  BlkioBounceBuf *bounce)
{
    QEMU_LOCK_GUARD(&s->bounce_lock);

    QLIST_REMOVE(bounce, next);

    /* Wake up waiting coroutines since space may now be available */
    qemu_co_queue_next(&s->bounce_available);
}

/* For async to .bdrv_co_*() conversion */
typedef struct {
    Coroutine *coroutine;
    int ret;
} BlkioCoData;

static void blkio_completion_fd_read(void *opaque)
{
    BlockDriverState *bs = opaque;
    BDRVBlkioState *s = bs->opaque;
    uint64_t val;
    int ret;

    /* Polling may have already fetched a completion */
    if (s->poll_completion.user_data != NULL) {
        BlkioCoData *cod = s->poll_completion.user_data;
        cod->ret = s->poll_completion.ret;

        /* Clear it in case aio_co_wake() enters a nested event loop */
        s->poll_completion.user_data = NULL;

        aio_co_wake(cod->coroutine);
    }

    /* Reset completion fd status */
    ret = read(s->completion_fd, &val, sizeof(val));

    /* Ignore errors, there's nothing we can do */
    (void)ret;

    /*
     * Reading one completion at a time makes nested event loop re-entrancy
     * simple. Change this loop to get multiple completions in one go if it
     * becomes a performance bottleneck.
     */
    while (true) {
        struct blkio_completion completion;

        WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
            ret = blkioq_do_io(s->blkioq, &completion, 0, 1, NULL);
        }
        if (ret != 1) {
            break;
        }

        BlkioCoData *cod = completion.user_data;
        cod->ret = completion.ret;
        aio_co_wake(cod->coroutine);
    }
}

static bool blkio_completion_fd_poll(void *opaque)
{
    BlockDriverState *bs = opaque;
    BDRVBlkioState *s = bs->opaque;
    int ret;

    /* Just in case we already fetched a completion */
    if (s->poll_completion.user_data != NULL) {
        return true;
    }

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        ret = blkioq_do_io(s->blkioq, &s->poll_completion, 0, 1, NULL);
    }
    return ret == 1;
}

static void blkio_completion_fd_poll_ready(void *opaque)
{
    blkio_completion_fd_read(opaque);
}

static void blkio_attach_aio_context(BlockDriverState *bs,
                                     AioContext *new_context)
{
    BDRVBlkioState *s = bs->opaque;

    aio_set_fd_handler(new_context,
                       s->completion_fd,
                       false,
                       blkio_completion_fd_read,
                       NULL,
                       blkio_completion_fd_poll,
                       blkio_completion_fd_poll_ready,
                       bs);
}

static void blkio_detach_aio_context(BlockDriverState *bs)
{
    BDRVBlkioState *s = bs->opaque;

    aio_set_fd_handler(bdrv_get_aio_context(bs),
                       s->completion_fd,
                       false, NULL, NULL, NULL, NULL, NULL);
}

/* Call with s->blkio_lock held to submit I/O after enqueuing a new request */
static void blkio_submit_io(BlockDriverState *bs)
{
    if (qatomic_read(&bs->io_plugged) == 0) {
        BDRVBlkioState *s = bs->opaque;

        blkioq_do_io(s->blkioq, NULL, 0, 0, NULL);
    }
}

static int coroutine_fn
blkio_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)
{
    BDRVBlkioState *s = bs->opaque;
    BlkioCoData cod = {
        .coroutine = qemu_coroutine_self(),
    };

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkioq_discard(s->blkioq, offset, bytes, &cod, 0);
        blkio_submit_io(bs);
    }

    qemu_coroutine_yield();
    return cod.ret;
}

static int coroutine_fn
blkio_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
                QEMUIOVector *qiov, BdrvRequestFlags flags)
{
    BlkioCoData cod = {
        .coroutine = qemu_coroutine_self(),
    };
    BDRVBlkioState *s = bs->opaque;
    bool use_bounce_buffer =
        s->needs_mem_regions && !(flags & BDRV_REQ_REGISTERED_BUF);
    BlkioBounceBuf bounce;
    struct iovec *iov = qiov->iov;
    int iovcnt = qiov->niov;

    if (use_bounce_buffer) {
        int ret = blkio_alloc_bounce_buffer(s, &bounce, bytes);
        if (ret < 0) {
            return ret;
        }

        iov = &bounce.buf;
        iovcnt = 1;
    }

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkioq_readv(s->blkioq, offset, iov, iovcnt, &cod, 0);
        blkio_submit_io(bs);
    }

    qemu_coroutine_yield();

    if (use_bounce_buffer) {
        if (cod.ret == 0) {
            qemu_iovec_from_buf(qiov, 0,
                                bounce.buf.iov_base,
                                bounce.buf.iov_len);
        }

        blkio_free_bounce_buffer(s, &bounce);
    }

    return cod.ret;
}

static int coroutine_fn blkio_co_pwritev(BlockDriverState *bs, int64_t offset,
        int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags)
{
    uint32_t blkio_flags = (flags & BDRV_REQ_FUA) ? BLKIO_REQ_FUA : 0;
    BlkioCoData cod = {
        .coroutine = qemu_coroutine_self(),
    };
    BDRVBlkioState *s = bs->opaque;
    bool use_bounce_buffer =
        s->needs_mem_regions && !(flags & BDRV_REQ_REGISTERED_BUF);
    BlkioBounceBuf bounce;
    struct iovec *iov = qiov->iov;
    int iovcnt = qiov->niov;

    if (use_bounce_buffer) {
        int ret = blkio_alloc_bounce_buffer(s, &bounce, bytes);
        if (ret < 0) {
            return ret;
        }

        qemu_iovec_to_buf(qiov, 0, bounce.buf.iov_base, bytes);
        iov = &bounce.buf;
        iovcnt = 1;
    }

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkioq_writev(s->blkioq, offset, iov, iovcnt, &cod, blkio_flags);
        blkio_submit_io(bs);
    }

    qemu_coroutine_yield();

    if (use_bounce_buffer) {
        blkio_free_bounce_buffer(s, &bounce);
    }

    return cod.ret;
}

static int coroutine_fn blkio_co_flush(BlockDriverState *bs)
{
    BDRVBlkioState *s = bs->opaque;
    BlkioCoData cod = {
        .coroutine = qemu_coroutine_self(),
    };

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkioq_flush(s->blkioq, &cod, 0);
        blkio_submit_io(bs);
    }

    qemu_coroutine_yield();
    return cod.ret;
}

static int coroutine_fn blkio_co_pwrite_zeroes(BlockDriverState *bs,
    int64_t offset, int64_t bytes, BdrvRequestFlags flags)
{
    BDRVBlkioState *s = bs->opaque;
    BlkioCoData cod = {
        .coroutine = qemu_coroutine_self(),
    };
    uint32_t blkio_flags = 0;

    if (flags & BDRV_REQ_FUA) {
        blkio_flags |= BLKIO_REQ_FUA;
    }
    if (!(flags & BDRV_REQ_MAY_UNMAP)) {
        blkio_flags |= BLKIO_REQ_NO_UNMAP;
    }
    if (flags & BDRV_REQ_NO_FALLBACK) {
        blkio_flags |= BLKIO_REQ_NO_FALLBACK;
    }

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkioq_write_zeroes(s->blkioq, offset, bytes, &cod, blkio_flags);
        blkio_submit_io(bs);
    }

    qemu_coroutine_yield();
    return cod.ret;
}

static void blkio_io_unplug(BlockDriverState *bs)
{
    BDRVBlkioState *s = bs->opaque;

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkio_submit_io(bs);
    }
}

typedef enum {
    BMRR_OK,
    BMRR_SKIP,
    BMRR_FAIL,
} BlkioMemRegionResult;

/*
 * Produce a struct blkio_mem_region for a given address and size.
 *
 * This function produces identical results when called multiple times with the
 * same arguments. This property is necessary because blkio_unmap_mem_region()
 * must receive the same struct blkio_mem_region field values that were passed
 * to blkio_map_mem_region().
 */
static BlkioMemRegionResult
blkio_mem_region_from_host(BlockDriverState *bs,
                           void *host, size_t size,
                           struct blkio_mem_region *region,
                           Error **errp)
{
    BDRVBlkioState *s = bs->opaque;
    int fd = -1;
    ram_addr_t fd_offset = 0;

    if (((uintptr_t)host | size) % s->mem_region_alignment) {
        error_setg(errp, "unaligned buf %p with size %zu", host, size);
        return BMRR_FAIL;
    }

    /* Attempt to find the fd for the underlying memory */
    if (s->needs_mem_region_fd) {
        RAMBlock *ram_block;
        RAMBlock *end_block;
        ram_addr_t offset;

        /*
         * bdrv_register_buf() is called with the BQL held so mr lives at least
         * until this function returns.
         */
        ram_block = qemu_ram_block_from_host(host, false, &fd_offset);
        if (ram_block) {
            fd = qemu_ram_get_fd(ram_block);
        }
        if (fd == -1) {
            /*
             * Ideally every RAMBlock would have an fd. pc-bios and other
             * things don't. Luckily they are usually not I/O buffers and we
             * can just ignore them.
             */
            return BMRR_SKIP;
        }

        /* Make sure the fd covers the entire range */
        end_block = qemu_ram_block_from_host(host + size - 1, false, &offset);
        if (ram_block != end_block) {
            error_setg(errp, "registered buffer at %p with size %zu extends "
                       "beyond RAMBlock", host, size);
            return BMRR_FAIL;
        }
    }

    *region = (struct blkio_mem_region){
        .addr = host,
        .len = size,
        .fd = fd,
        .fd_offset = fd_offset,
    };
    return BMRR_OK;
}

static bool blkio_register_buf(BlockDriverState *bs, void *host, size_t size,
                               Error **errp)
{
    BDRVBlkioState *s = bs->opaque;
    struct blkio_mem_region region;
    BlkioMemRegionResult region_result;
    int ret;

    /*
     * Mapping memory regions conflicts with RAM discard (virtio-mem) when
     * there is pinning, so only do it when necessary.
     */
    if (!s->needs_mem_regions && s->may_pin_mem_regions) {
        return true;
    }

    region_result = blkio_mem_region_from_host(bs, host, size, &region, errp);
    if (region_result == BMRR_SKIP) {
        return true;
    } else if (region_result != BMRR_OK) {
        return false;
    }

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        ret = blkio_map_mem_region(s->blkio, &region);
    }

    if (ret < 0) {
        error_setg(errp, "Failed to add blkio mem region %p with size %zu: %s",
                   host, size, blkio_get_error_msg());
        return false;
    }
    return true;
}

static void blkio_unregister_buf(BlockDriverState *bs, void *host, size_t size)
{
    BDRVBlkioState *s = bs->opaque;
    struct blkio_mem_region region;

    /* See blkio_register_buf() */
    if (!s->needs_mem_regions && s->may_pin_mem_regions) {
        return;
    }

    if (blkio_mem_region_from_host(bs, host, size, &region, NULL) != BMRR_OK) {
        return;
    }

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        blkio_unmap_mem_region(s->blkio, &region);
    }
}

static int blkio_io_uring_open(BlockDriverState *bs, QDict *options, int flags,
                               Error **errp)
{
    const char *filename = qdict_get_str(options, "filename");
    BDRVBlkioState *s = bs->opaque;
    int ret;

    ret = blkio_set_str(s->blkio, "path", filename);
    qdict_del(options, "filename");
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to set path: %s",
                         blkio_get_error_msg());
        return ret;
    }

    if (flags & BDRV_O_NOCACHE) {
        ret = blkio_set_bool(s->blkio, "direct", true);
        if (ret < 0) {
            error_setg_errno(errp, -ret, "failed to set direct: %s",
                             blkio_get_error_msg());
            return ret;
        }
    }

    return 0;
}

static int blkio_nvme_io_uring(BlockDriverState *bs, QDict *options, int flags,
                               Error **errp)
{
    const char *filename = qdict_get_str(options, "filename");
    BDRVBlkioState *s = bs->opaque;
    int ret;

    ret = blkio_set_str(s->blkio, "path", filename);
    qdict_del(options, "filename");
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to set path: %s",
                         blkio_get_error_msg());
        return ret;
    }

    if (!(flags & BDRV_O_NOCACHE)) {
        error_setg(errp, "cache.direct=off is not supported");
        return -EINVAL;
    }

    return 0;
}

static int blkio_virtio_blk_common_open(BlockDriverState *bs,
        QDict *options, int flags, Error **errp)
{
    const char *path = qdict_get_try_str(options, "path");
    BDRVBlkioState *s = bs->opaque;
    int ret;

    if (!path) {
        error_setg(errp, "missing 'path' option");
        return -EINVAL;
    }

    ret = blkio_set_str(s->blkio, "path", path);
    qdict_del(options, "path");
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to set path: %s",
                         blkio_get_error_msg());
        return ret;
    }

    if (!(flags & BDRV_O_NOCACHE)) {
        error_setg(errp, "cache.direct=off is not supported");
        return -EINVAL;
    }
    return 0;
}

static int blkio_file_open(BlockDriverState *bs, QDict *options, int flags,
                           Error **errp)
{
    const char *blkio_driver = bs->drv->protocol_name;
    BDRVBlkioState *s = bs->opaque;
    int ret;

    ret = blkio_create(blkio_driver, &s->blkio);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "blkio_create failed: %s",
                         blkio_get_error_msg());
        return ret;
    }

    if (strcmp(blkio_driver, DRIVER_IO_URING) == 0) {
        ret = blkio_io_uring_open(bs, options, flags, errp);
    } else if (strcmp(blkio_driver, DRIVER_NVME_IO_URING) == 0) {
        ret = blkio_nvme_io_uring(bs, options, flags, errp);
    } else if (strcmp(blkio_driver, DRIVER_VIRTIO_BLK_VHOST_USER) == 0) {
        ret = blkio_virtio_blk_common_open(bs, options, flags, errp);
    } else if (strcmp(blkio_driver, DRIVER_VIRTIO_BLK_VHOST_VDPA) == 0) {
        ret = blkio_virtio_blk_common_open(bs, options, flags, errp);
    } else {
        g_assert_not_reached();
    }
    if (ret < 0) {
        blkio_destroy(&s->blkio);
        return ret;
    }

    if (!(flags & BDRV_O_RDWR)) {
        ret = blkio_set_bool(s->blkio, "read-only", true);
        if (ret < 0) {
            error_setg_errno(errp, -ret, "failed to set read-only: %s",
                             blkio_get_error_msg());
            blkio_destroy(&s->blkio);
            return ret;
        }
    }

    ret = blkio_connect(s->blkio);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "blkio_connect failed: %s",
                         blkio_get_error_msg());
        blkio_destroy(&s->blkio);
        return ret;
    }

    ret = blkio_get_bool(s->blkio,
                         "needs-mem-regions",
                         &s->needs_mem_regions);
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "failed to get needs-mem-regions: %s",
                         blkio_get_error_msg());
        blkio_destroy(&s->blkio);
        return ret;
    }

    ret = blkio_get_bool(s->blkio,
                         "needs-mem-region-fd",
                         &s->needs_mem_region_fd);
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "failed to get needs-mem-region-fd: %s",
                         blkio_get_error_msg());
        blkio_destroy(&s->blkio);
        return ret;
    }

    ret = blkio_get_uint64(s->blkio,
                           "mem-region-alignment",
                           &s->mem_region_alignment);
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "failed to get mem-region-alignment: %s",
                         blkio_get_error_msg());
        blkio_destroy(&s->blkio);
        return ret;
    }

    ret = blkio_get_bool(s->blkio,
                         "may-pin-mem-regions",
                         &s->may_pin_mem_regions);
    if (ret < 0) {
        /* Be conservative (assume pinning) if the property is not supported */
        s->may_pin_mem_regions = s->needs_mem_regions;
    }

    /*
     * Notify if libblkio drivers pin memory and prevent features like
     * virtio-mem from working.
     */
    if (s->may_pin_mem_regions) {
        ret = ram_block_discard_disable(true);
        if (ret < 0) {
            error_setg_errno(errp, -ret, "ram_block_discard_disable() failed");
            blkio_destroy(&s->blkio);
            return ret;
        }
    }

    ret = blkio_start(s->blkio);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "blkio_start failed: %s",
                         blkio_get_error_msg());
        blkio_destroy(&s->blkio);
        if (s->may_pin_mem_regions) {
            ram_block_discard_disable(false);
        }
        return ret;
    }

    bs->supported_write_flags = BDRV_REQ_FUA | BDRV_REQ_REGISTERED_BUF;
    bs->supported_zero_flags = BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP |
                               BDRV_REQ_NO_FALLBACK;

    qemu_mutex_init(&s->blkio_lock);
    qemu_co_mutex_init(&s->bounce_lock);
    qemu_co_queue_init(&s->bounce_available);
    QLIST_INIT(&s->bounce_bufs);
    s->blkioq = blkio_get_queue(s->blkio, 0);
    s->completion_fd = blkioq_get_completion_fd(s->blkioq);

    blkio_attach_aio_context(bs, bdrv_get_aio_context(bs));
    return 0;
}

static void blkio_close(BlockDriverState *bs)
{
    BDRVBlkioState *s = bs->opaque;

    /* There is no destroy() API for s->bounce_lock */

    qemu_mutex_destroy(&s->blkio_lock);
    blkio_detach_aio_context(bs);
    blkio_destroy(&s->blkio);

    if (s->may_pin_mem_regions) {
        ram_block_discard_disable(false);
    }
}

static int64_t blkio_getlength(BlockDriverState *bs)
{
    BDRVBlkioState *s = bs->opaque;
    uint64_t capacity;
    int ret;

    WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {
        ret = blkio_get_uint64(s->blkio, "capacity", &capacity);
    }
    if (ret < 0) {
        return -ret;
    }

    return capacity;
}

static int blkio_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
    return 0;
}

static void blkio_refresh_limits(BlockDriverState *bs, Error **errp)
{
    BDRVBlkioState *s = bs->opaque;
    QEMU_LOCK_GUARD(&s->blkio_lock);
    int value;
    int ret;

    ret = blkio_get_int(s->blkio, "request-alignment", &value);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to get \"request-alignment\": %s",
                         blkio_get_error_msg());
        return;
    }
    bs->bl.request_alignment = value;
    if (bs->bl.request_alignment < 1 ||
        bs->bl.request_alignment >= INT_MAX ||
        !is_power_of_2(bs->bl.request_alignment)) {
        error_setg(errp, "invalid \"request-alignment\" value %" PRIu32 ", "
                   "must be a power of 2 less than INT_MAX",
                   bs->bl.request_alignment);
        return;
    }

    ret = blkio_get_int(s->blkio, "optimal-io-size", &value);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to get \"optimal-io-size\": %s",
                         blkio_get_error_msg());
        return;
    }
    bs->bl.opt_transfer = value;
    if (bs->bl.opt_transfer > INT_MAX ||
        (bs->bl.opt_transfer % bs->bl.request_alignment)) {
        error_setg(errp, "invalid \"optimal-io-size\" value %" PRIu32 ", must "
                   "be a multiple of %" PRIu32, bs->bl.opt_transfer,
                   bs->bl.request_alignment);
        return;
    }

    ret = blkio_get_int(s->blkio, "max-transfer", &value);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to get \"max-transfer\": %s",
                         blkio_get_error_msg());
        return;
    }
    bs->bl.max_transfer = value;
    if ((bs->bl.max_transfer % bs->bl.request_alignment) ||
        (bs->bl.opt_transfer && (bs->bl.max_transfer % bs->bl.opt_transfer))) {
        error_setg(errp, "invalid \"max-transfer\" value %" PRIu32 ", must be "
                   "a multiple of %" PRIu32 " and %" PRIu32 " (if non-zero)",
                   bs->bl.max_transfer, bs->bl.request_alignment,
                   bs->bl.opt_transfer);
        return;
    }

    ret = blkio_get_int(s->blkio, "buf-alignment", &value);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to get \"buf-alignment\": %s",
                         blkio_get_error_msg());
        return;
    }
    if (value < 1) {
        error_setg(errp, "invalid \"buf-alignment\" value %d, must be "
                   "positive", value);
        return;
    }
    bs->bl.min_mem_alignment = value;

    ret = blkio_get_int(s->blkio, "optimal-buf-alignment", &value);
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "failed to get \"optimal-buf-alignment\": %s",
                         blkio_get_error_msg());
        return;
    }
    if (value < 1) {
        error_setg(errp, "invalid \"optimal-buf-alignment\" value %d, "
                   "must be positive", value);
        return;
    }
    bs->bl.opt_mem_alignment = value;

    ret = blkio_get_int(s->blkio, "max-segments", &value);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "failed to get \"max-segments\": %s",
                         blkio_get_error_msg());
        return;
    }
    if (value < 1) {
        error_setg(errp, "invalid \"max-segments\" value %d, must be positive",
                   value);
        return;
    }
    bs->bl.max_iov = value;
}

/*
 * TODO
 * Missing libblkio APIs:
 * - block_status
 * - co_invalidate_cache
 *
 * Out of scope?
 * - create
 * - truncate
 */

#define BLKIO_DRIVER(name, ...) \
    { \
        .format_name             = name, \
        .protocol_name           = name, \
        .instance_size           = sizeof(BDRVBlkioState), \
        .bdrv_file_open          = blkio_file_open, \
        .bdrv_close              = blkio_close, \
        .bdrv_getlength          = blkio_getlength, \
        .bdrv_get_info           = blkio_get_info, \
        .bdrv_attach_aio_context = blkio_attach_aio_context, \
        .bdrv_detach_aio_context = blkio_detach_aio_context, \
        .bdrv_co_pdiscard        = blkio_co_pdiscard, \
        .bdrv_co_preadv          = blkio_co_preadv, \
        .bdrv_co_pwritev         = blkio_co_pwritev, \
        .bdrv_co_flush_to_disk   = blkio_co_flush, \
        .bdrv_co_pwrite_zeroes   = blkio_co_pwrite_zeroes, \
        .bdrv_io_unplug          = blkio_io_unplug, \
        .bdrv_refresh_limits     = blkio_refresh_limits, \
        .bdrv_register_buf       = blkio_register_buf, \
        .bdrv_unregister_buf     = blkio_unregister_buf, \
        __VA_ARGS__ \
    }

static BlockDriver bdrv_io_uring = BLKIO_DRIVER(
    DRIVER_IO_URING,
    .bdrv_needs_filename = true,
);

static BlockDriver bdrv_nvme_io_uring = BLKIO_DRIVER(
    DRIVER_NVME_IO_URING,
    .bdrv_needs_filename = true,
);

static BlockDriver bdrv_virtio_blk_vhost_user = BLKIO_DRIVER(
    DRIVER_VIRTIO_BLK_VHOST_USER
);

static BlockDriver bdrv_virtio_blk_vhost_vdpa = BLKIO_DRIVER(
    DRIVER_VIRTIO_BLK_VHOST_VDPA
);

static void bdrv_blkio_init(void)
{
    bdrv_register(&bdrv_io_uring);
    bdrv_register(&bdrv_nvme_io_uring);
    bdrv_register(&bdrv_virtio_blk_vhost_user);
    bdrv_register(&bdrv_virtio_blk_vhost_vdpa);
}

block_init(bdrv_blkio_init);