block-backend.c 29.6 KB
Newer Older
M
Markus Armbruster 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * QEMU Block backends
 *
 * Copyright (C) 2014 Red Hat, Inc.
 *
 * Authors:
 *  Markus Armbruster <armbru@redhat.com>,
 *
 * This work is licensed under the terms of the GNU LGPL, version 2.1
 * or later.  See the COPYING.LIB file in the top-level directory.
 */

#include "sysemu/block-backend.h"
#include "block/block_int.h"
15
#include "block/blockjob.h"
M
Max Reitz 已提交
16
#include "block/throttle-groups.h"
17
#include "sysemu/blockdev.h"
18
#include "sysemu/sysemu.h"
19 20 21 22
#include "qapi-event.h"

/* Number of coroutines to reserve per attached device model */
#define COROUTINE_POOL_RESERVATION 64
M
Markus Armbruster 已提交
23

24 25
static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb);

M
Markus Armbruster 已提交
26 27 28
struct BlockBackend {
    char *name;
    int refcnt;
29
    BlockDriverState *bs;
30
    DriveInfo *legacy_dinfo;    /* null unless created by drive_new() */
M
Markus Armbruster 已提交
31
    QTAILQ_ENTRY(BlockBackend) link; /* for blk_backends */
32 33 34 35 36

    void *dev;                  /* attached device model, if any */
    /* TODO change to DeviceState when all users are qdevified */
    const BlockDevOps *dev_ops;
    void *dev_opaque;
37 38 39

    /* the block size for which the guest device expects atomicity */
    int guest_block_size;
40

M
Max Reitz 已提交
41 42 43 44
    /* If the BDS tree is removed, some of its options are stored here (which
     * can be used to restore those options in the new BDS on insert) */
    BlockBackendRootState root_state;

45 46
    /* I/O stats (display with "info blockstats"). */
    BlockAcctStats stats;
47 48 49 50

    BlockdevOnError on_read_error, on_write_error;
    bool iostatus_enabled;
    BlockDeviceIoStatus iostatus;
M
Markus Armbruster 已提交
51 52
};

M
Max Reitz 已提交
53 54 55
typedef struct BlockBackendAIOCB {
    BlockAIOCB common;
    QEMUBH *bh;
56
    BlockBackend *blk;
M
Max Reitz 已提交
57 58 59 60
    int ret;
} BlockBackendAIOCB;

static const AIOCBInfo block_backend_aiocb_info = {
61
    .get_aio_context = blk_aiocb_get_aio_context,
M
Max Reitz 已提交
62 63 64
    .aiocb_size = sizeof(BlockBackendAIOCB),
};

65 66
static void drive_info_del(DriveInfo *dinfo);

67
/* All the BlockBackends (except for hidden ones) */
M
Markus Armbruster 已提交
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
static QTAILQ_HEAD(, BlockBackend) blk_backends =
    QTAILQ_HEAD_INITIALIZER(blk_backends);

/*
 * Create a new BlockBackend with @name, with a reference count of one.
 * @name must not be null or empty.
 * Fail if a BlockBackend with this name already exists.
 * Store an error through @errp on failure, unless it's null.
 * Return the new BlockBackend on success, null on failure.
 */
BlockBackend *blk_new(const char *name, Error **errp)
{
    BlockBackend *blk;

    assert(name && name[0]);
83 84 85 86
    if (!id_wellformed(name)) {
        error_setg(errp, "Invalid device name");
        return NULL;
    }
M
Markus Armbruster 已提交
87 88 89 90
    if (blk_by_name(name)) {
        error_setg(errp, "Device with id '%s' already exists", name);
        return NULL;
    }
91 92 93 94 95 96
    if (bdrv_find_node(name)) {
        error_setg(errp,
                   "Device name '%s' conflicts with an existing node name",
                   name);
        return NULL;
    }
M
Markus Armbruster 已提交
97 98 99 100 101 102 103 104

    blk = g_new0(BlockBackend, 1);
    blk->name = g_strdup(name);
    blk->refcnt = 1;
    QTAILQ_INSERT_TAIL(&blk_backends, blk, link);
    return blk;
}

105 106 107 108 109 110 111 112 113 114 115 116 117 118
/*
 * Create a new BlockBackend with a new BlockDriverState attached.
 * Otherwise just like blk_new(), which see.
 */
BlockBackend *blk_new_with_bs(const char *name, Error **errp)
{
    BlockBackend *blk;
    BlockDriverState *bs;

    blk = blk_new(name, errp);
    if (!blk) {
        return NULL;
    }

119
    bs = bdrv_new_root();
120 121 122 123 124
    blk->bs = bs;
    bs->blk = blk;
    return blk;
}

M
Max Reitz 已提交
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
/*
 * Calls blk_new_with_bs() and then calls bdrv_open() on the BlockDriverState.
 *
 * Just as with bdrv_open(), after having called this function the reference to
 * @options belongs to the block layer (even on failure).
 *
 * TODO: Remove @filename and @flags; it should be possible to specify a whole
 * BDS tree just by specifying the @options QDict (or @reference,
 * alternatively). At the time of adding this function, this is not possible,
 * though, so callers of this function have to be able to specify @filename and
 * @flags.
 */
BlockBackend *blk_new_open(const char *name, const char *filename,
                           const char *reference, QDict *options, int flags,
                           Error **errp)
{
    BlockBackend *blk;
    int ret;

    blk = blk_new_with_bs(name, errp);
    if (!blk) {
        QDECREF(options);
        return NULL;
    }

150
    ret = bdrv_open(&blk->bs, filename, reference, options, flags, errp);
M
Max Reitz 已提交
151 152 153 154 155 156 157 158
    if (ret < 0) {
        blk_unref(blk);
        return NULL;
    }

    return blk;
}

M
Markus Armbruster 已提交
159 160 161
static void blk_delete(BlockBackend *blk)
{
    assert(!blk->refcnt);
162
    assert(!blk->dev);
163
    if (blk->bs) {
164
        assert(blk->bs->blk == blk);
165
        blk->bs->blk = NULL;
166
        bdrv_unref(blk->bs);
167 168
        blk->bs = NULL;
    }
M
Max Reitz 已提交
169 170 171 172
    if (blk->root_state.throttle_state) {
        g_free(blk->root_state.throttle_group);
        throttle_group_unref(blk->root_state.throttle_state);
    }
173
    /* Avoid double-remove after blk_hide_on_behalf_of_hmp_drive_del() */
174 175 176
    if (blk->name[0]) {
        QTAILQ_REMOVE(&blk_backends, blk, link);
    }
M
Markus Armbruster 已提交
177
    g_free(blk->name);
178
    drive_info_del(blk->legacy_dinfo);
M
Markus Armbruster 已提交
179 180 181
    g_free(blk);
}

182 183 184 185 186 187 188 189 190 191
static void drive_info_del(DriveInfo *dinfo)
{
    if (!dinfo) {
        return;
    }
    qemu_opts_del(dinfo->opts);
    g_free(dinfo->serial);
    g_free(dinfo);
}

M
Markus Armbruster 已提交
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
/*
 * Increment @blk's reference count.
 * @blk must not be null.
 */
void blk_ref(BlockBackend *blk)
{
    blk->refcnt++;
}

/*
 * Decrement @blk's reference count.
 * If this drops it to zero, destroy @blk.
 * For convenience, do nothing if @blk is null.
 */
void blk_unref(BlockBackend *blk)
{
    if (blk) {
        assert(blk->refcnt > 0);
        if (!--blk->refcnt) {
            blk_delete(blk);
        }
    }
}

/*
 * Return the BlockBackend after @blk.
 * If @blk is null, return the first one.
 * Else, return @blk's next sibling, which may be null.
 *
 * To iterate over all BlockBackends, do
 * for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
 *     ...
 * }
 */
BlockBackend *blk_next(BlockBackend *blk)
{
    return blk ? QTAILQ_NEXT(blk, link) : QTAILQ_FIRST(&blk_backends);
}

/*
232 233
 * Return @blk's name, a non-null string.
 * Wart: the name is empty iff @blk has been hidden with
234
 * blk_hide_on_behalf_of_hmp_drive_del().
M
Markus Armbruster 已提交
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
 */
const char *blk_name(BlockBackend *blk)
{
    return blk->name;
}

/*
 * Return the BlockBackend with name @name if it exists, else null.
 * @name must not be null.
 */
BlockBackend *blk_by_name(const char *name)
{
    BlockBackend *blk;

    assert(name);
    QTAILQ_FOREACH(blk, &blk_backends, link) {
        if (!strcmp(name, blk->name)) {
            return blk;
        }
    }
    return NULL;
}
257 258 259 260 261 262 263 264 265

/*
 * Return the BlockDriverState attached to @blk if any, else null.
 */
BlockDriverState *blk_bs(BlockBackend *blk)
{
    return blk->bs;
}

K
Kevin Wolf 已提交
266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
/*
 * Changes the BlockDriverState attached to @blk
 */
void blk_set_bs(BlockBackend *blk, BlockDriverState *bs)
{
    bdrv_ref(bs);

    if (blk->bs) {
        blk->bs->blk = NULL;
        bdrv_unref(blk->bs);
    }
    assert(bs->blk == NULL);

    blk->bs = bs;
    bs->blk = blk;
}

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
/*
 * Return @blk's DriveInfo if any, else null.
 */
DriveInfo *blk_legacy_dinfo(BlockBackend *blk)
{
    return blk->legacy_dinfo;
}

/*
 * Set @blk's DriveInfo to @dinfo, and return it.
 * @blk must not have a DriveInfo set already.
 * No other BlockBackend may have the same DriveInfo set.
 */
DriveInfo *blk_set_legacy_dinfo(BlockBackend *blk, DriveInfo *dinfo)
{
    assert(!blk->legacy_dinfo);
    return blk->legacy_dinfo = dinfo;
}

/*
 * Return the BlockBackend with DriveInfo @dinfo.
 * It must exist.
 */
BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo)
{
    BlockBackend *blk;

    QTAILQ_FOREACH(blk, &blk_backends, link) {
        if (blk->legacy_dinfo == dinfo) {
            return blk;
        }
    }
    abort();
}

318 319 320 321 322 323 324 325 326
/*
 * Hide @blk.
 * @blk must not have been hidden already.
 * Make attached BlockDriverState, if any, anonymous.
 * Once hidden, @blk is invisible to all functions that don't receive
 * it as argument.  For example, blk_by_name() won't return it.
 * Strictly for use by do_drive_del().
 * TODO get rid of it!
 */
327
void blk_hide_on_behalf_of_hmp_drive_del(BlockBackend *blk)
328 329 330 331 332 333 334
{
    QTAILQ_REMOVE(&blk_backends, blk, link);
    blk->name[0] = 0;
    if (blk->bs) {
        bdrv_make_anon(blk->bs);
    }
}
335

336 337 338 339
/*
 * Attach device model @dev to @blk.
 * Return 0 on success, -EBUSY when a device model is attached already.
 */
340
int blk_attach_dev(BlockBackend *blk, void *dev)
341
/* TODO change to DeviceState *dev when all users are qdevified */
342
{
343 344 345
    if (blk->dev) {
        return -EBUSY;
    }
346
    blk_ref(blk);
347
    blk->dev = dev;
348
    blk_iostatus_reset(blk);
349
    return 0;
350 351
}

352 353 354 355 356
/*
 * Attach device model @dev to @blk.
 * @blk must not have a device model attached already.
 * TODO qdevified devices don't use this, remove when devices are qdevified
 */
357 358
void blk_attach_dev_nofail(BlockBackend *blk, void *dev)
{
359 360 361
    if (blk_attach_dev(blk, dev) < 0) {
        abort();
    }
362 363
}

364 365 366 367
/*
 * Detach device model @dev from @blk.
 * @dev must be currently attached to @blk.
 */
368
void blk_detach_dev(BlockBackend *blk, void *dev)
369
/* TODO change to DeviceState *dev when all users are qdevified */
370
{
371 372 373 374
    assert(blk->dev == dev);
    blk->dev = NULL;
    blk->dev_ops = NULL;
    blk->dev_opaque = NULL;
375
    blk->guest_block_size = 512;
376
    blk_unref(blk);
377 378
}

379 380 381
/*
 * Return the device model attached to @blk if any, else null.
 */
382
void *blk_get_attached_dev(BlockBackend *blk)
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
/* TODO change to return DeviceState * when all users are qdevified */
{
    return blk->dev;
}

/*
 * Set @blk's device model callbacks to @ops.
 * @opaque is the opaque argument to pass to the callbacks.
 * This is for use by device models.
 */
void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
                     void *opaque)
{
    blk->dev_ops = ops;
    blk->dev_opaque = opaque;
}

/*
 * Notify @blk's attached device model of media change.
 * If @load is true, notify of media load.
 * Else, notify of media eject.
 * Also send DEVICE_TRAY_MOVED events as appropriate.
 */
void blk_dev_change_media_cb(BlockBackend *blk, bool load)
{
    if (blk->dev_ops && blk->dev_ops->change_media_cb) {
        bool tray_was_closed = !blk_dev_is_tray_open(blk);

        blk->dev_ops->change_media_cb(blk->dev_opaque, load);
        if (tray_was_closed) {
            /* tray open */
            qapi_event_send_device_tray_moved(blk_name(blk),
                                              true, &error_abort);
        }
        if (load) {
            /* tray close */
            qapi_event_send_device_tray_moved(blk_name(blk),
                                              false, &error_abort);
        }
    }
}

/*
 * Does @blk's attached device model have removable media?
 * %true if no device model is attached.
 */
bool blk_dev_has_removable_media(BlockBackend *blk)
{
    return !blk->dev || (blk->dev_ops && blk->dev_ops->change_media_cb);
}

/*
 * Notify @blk's attached device model of a media eject request.
 * If @force is true, the medium is about to be yanked out forcefully.
 */
void blk_dev_eject_request(BlockBackend *blk, bool force)
439
{
440 441 442
    if (blk->dev_ops && blk->dev_ops->eject_request_cb) {
        blk->dev_ops->eject_request_cb(blk->dev_opaque, force);
    }
443 444
}

445 446 447 448
/*
 * Does @blk's attached device model have a tray, and is it open?
 */
bool blk_dev_is_tray_open(BlockBackend *blk)
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
    if (blk->dev_ops && blk->dev_ops->is_tray_open) {
        return blk->dev_ops->is_tray_open(blk->dev_opaque);
    }
    return false;
}

/*
 * Does @blk's attached device model have the medium locked?
 * %false if the device model has no such lock.
 */
bool blk_dev_is_medium_locked(BlockBackend *blk)
{
    if (blk->dev_ops && blk->dev_ops->is_medium_locked) {
        return blk->dev_ops->is_medium_locked(blk->dev_opaque);
    }
    return false;
}

/*
 * Notify @blk's attached device model of a backend size change.
 */
void blk_dev_resize_cb(BlockBackend *blk)
{
    if (blk->dev_ops && blk->dev_ops->resize_cb) {
        blk->dev_ops->resize_cb(blk->dev_opaque);
    }
}

void blk_iostatus_enable(BlockBackend *blk)
{
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
    blk->iostatus_enabled = true;
    blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
}

/* The I/O status is only enabled if the drive explicitly
 * enables it _and_ the VM is configured to stop on errors */
bool blk_iostatus_is_enabled(const BlockBackend *blk)
{
    return (blk->iostatus_enabled &&
           (blk->on_write_error == BLOCKDEV_ON_ERROR_ENOSPC ||
            blk->on_write_error == BLOCKDEV_ON_ERROR_STOP   ||
            blk->on_read_error == BLOCKDEV_ON_ERROR_STOP));
}

BlockDeviceIoStatus blk_iostatus(const BlockBackend *blk)
{
    return blk->iostatus;
}

void blk_iostatus_disable(BlockBackend *blk)
{
    blk->iostatus_enabled = false;
}

void blk_iostatus_reset(BlockBackend *blk)
{
    if (blk_iostatus_is_enabled(blk)) {
        blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
        if (blk->bs && blk->bs->job) {
            block_job_iostatus_reset(blk->bs->job);
        }
    }
}

void blk_iostatus_set_err(BlockBackend *blk, int error)
{
    assert(blk_iostatus_is_enabled(blk));
    if (blk->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
        blk->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
                                          BLOCK_DEVICE_IO_STATUS_FAILED;
    }
521 522
}

M
Max Reitz 已提交
523 524 525 526 527 528 529 530 531
static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
                                  size_t size)
{
    int64_t len;

    if (size > INT_MAX) {
        return -EIO;
    }

532
    if (!blk_is_available(blk)) {
M
Max Reitz 已提交
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
        return -ENOMEDIUM;
    }

    len = blk_getlength(blk);
    if (len < 0) {
        return len;
    }

    if (offset < 0) {
        return -EIO;
    }

    if (offset > len || len - offset < size) {
        return -EIO;
    }

    return 0;
}

static int blk_check_request(BlockBackend *blk, int64_t sector_num,
                             int nb_sectors)
{
    if (sector_num < 0 || sector_num > INT64_MAX / BDRV_SECTOR_SIZE) {
        return -EIO;
    }

    if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
        return -EIO;
    }

    return blk_check_byte_request(blk, sector_num * BDRV_SECTOR_SIZE,
                                  nb_sectors * BDRV_SECTOR_SIZE);
}

567 568 569
int blk_read(BlockBackend *blk, int64_t sector_num, uint8_t *buf,
             int nb_sectors)
{
M
Max Reitz 已提交
570 571 572 573 574
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

575 576 577 578 579 580
    return bdrv_read(blk->bs, sector_num, buf, nb_sectors);
}

int blk_read_unthrottled(BlockBackend *blk, int64_t sector_num, uint8_t *buf,
                         int nb_sectors)
{
M
Max Reitz 已提交
581 582 583 584 585
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

586 587 588 589 590 591
    return bdrv_read_unthrottled(blk->bs, sector_num, buf, nb_sectors);
}

int blk_write(BlockBackend *blk, int64_t sector_num, const uint8_t *buf,
              int nb_sectors)
{
M
Max Reitz 已提交
592 593 594 595 596
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

597 598 599
    return bdrv_write(blk->bs, sector_num, buf, nb_sectors);
}

600 601 602 603 604 605 606 607 608 609 610
int blk_write_zeroes(BlockBackend *blk, int64_t sector_num,
                     int nb_sectors, BdrvRequestFlags flags)
{
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

    return bdrv_write_zeroes(blk->bs, sector_num, nb_sectors, flags);
}

M
Max Reitz 已提交
611 612 613 614 615 616 617 618 619 620 621 622 623 624 625
static void error_callback_bh(void *opaque)
{
    struct BlockBackendAIOCB *acb = opaque;
    qemu_bh_delete(acb->bh);
    acb->common.cb(acb->common.opaque, acb->ret);
    qemu_aio_unref(acb);
}

static BlockAIOCB *abort_aio_request(BlockBackend *blk, BlockCompletionFunc *cb,
                                     void *opaque, int ret)
{
    struct BlockBackendAIOCB *acb;
    QEMUBH *bh;

    acb = blk_aio_get(&block_backend_aiocb_info, blk, cb, opaque);
626
    acb->blk = blk;
M
Max Reitz 已提交
627 628 629 630 631 632 633 634 635
    acb->ret = ret;

    bh = aio_bh_new(blk_get_aio_context(blk), error_callback_bh, acb);
    acb->bh = bh;
    qemu_bh_schedule(bh);

    return &acb->common;
}

636 637 638 639
BlockAIOCB *blk_aio_write_zeroes(BlockBackend *blk, int64_t sector_num,
                                 int nb_sectors, BdrvRequestFlags flags,
                                 BlockCompletionFunc *cb, void *opaque)
{
M
Max Reitz 已提交
640 641 642 643 644
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return abort_aio_request(blk, cb, opaque, ret);
    }

645 646 647 648 649 650
    return bdrv_aio_write_zeroes(blk->bs, sector_num, nb_sectors, flags,
                                 cb, opaque);
}

int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count)
{
M
Max Reitz 已提交
651 652 653 654 655
    int ret = blk_check_byte_request(blk, offset, count);
    if (ret < 0) {
        return ret;
    }

656 657 658 659 660
    return bdrv_pread(blk->bs, offset, buf, count);
}

int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count)
{
M
Max Reitz 已提交
661 662 663 664 665
    int ret = blk_check_byte_request(blk, offset, count);
    if (ret < 0) {
        return ret;
    }

666 667 668 669 670
    return bdrv_pwrite(blk->bs, offset, buf, count);
}

int64_t blk_getlength(BlockBackend *blk)
{
671 672 673 674
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

675 676 677 678 679 680 681 682
    return bdrv_getlength(blk->bs);
}

void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr)
{
    bdrv_get_geometry(blk->bs, nb_sectors_ptr);
}

683 684
int64_t blk_nb_sectors(BlockBackend *blk)
{
685 686 687 688
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

689 690 691
    return bdrv_nb_sectors(blk->bs);
}

692 693 694 695
BlockAIOCB *blk_aio_readv(BlockBackend *blk, int64_t sector_num,
                          QEMUIOVector *iov, int nb_sectors,
                          BlockCompletionFunc *cb, void *opaque)
{
M
Max Reitz 已提交
696 697 698 699 700
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return abort_aio_request(blk, cb, opaque, ret);
    }

701 702 703 704 705 706 707
    return bdrv_aio_readv(blk->bs, sector_num, iov, nb_sectors, cb, opaque);
}

BlockAIOCB *blk_aio_writev(BlockBackend *blk, int64_t sector_num,
                           QEMUIOVector *iov, int nb_sectors,
                           BlockCompletionFunc *cb, void *opaque)
{
M
Max Reitz 已提交
708 709 710 711 712
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return abort_aio_request(blk, cb, opaque, ret);
    }

713 714 715 716 717 718
    return bdrv_aio_writev(blk->bs, sector_num, iov, nb_sectors, cb, opaque);
}

BlockAIOCB *blk_aio_flush(BlockBackend *blk,
                          BlockCompletionFunc *cb, void *opaque)
{
719 720 721 722
    if (!blk_is_available(blk)) {
        return abort_aio_request(blk, cb, opaque, -ENOMEDIUM);
    }

723 724 725 726 727 728 729
    return bdrv_aio_flush(blk->bs, cb, opaque);
}

BlockAIOCB *blk_aio_discard(BlockBackend *blk,
                            int64_t sector_num, int nb_sectors,
                            BlockCompletionFunc *cb, void *opaque)
{
M
Max Reitz 已提交
730 731 732 733 734
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return abort_aio_request(blk, cb, opaque, ret);
    }

735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
    return bdrv_aio_discard(blk->bs, sector_num, nb_sectors, cb, opaque);
}

void blk_aio_cancel(BlockAIOCB *acb)
{
    bdrv_aio_cancel(acb);
}

void blk_aio_cancel_async(BlockAIOCB *acb)
{
    bdrv_aio_cancel_async(acb);
}

int blk_aio_multiwrite(BlockBackend *blk, BlockRequest *reqs, int num_reqs)
{
M
Max Reitz 已提交
750 751 752 753 754 755 756 757 758
    int i, ret;

    for (i = 0; i < num_reqs; i++) {
        ret = blk_check_request(blk, reqs[i].sector, reqs[i].nb_sectors);
        if (ret < 0) {
            return ret;
        }
    }

759 760 761 762 763
    return bdrv_aio_multiwrite(blk->bs, reqs, num_reqs);
}

int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
{
764 765 766 767
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

768 769 770 771 772 773
    return bdrv_ioctl(blk->bs, req, buf);
}

BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
                          BlockCompletionFunc *cb, void *opaque)
{
774 775 776 777
    if (!blk_is_available(blk)) {
        return abort_aio_request(blk, cb, opaque, -ENOMEDIUM);
    }

778 779 780
    return bdrv_aio_ioctl(blk->bs, req, buf, cb, opaque);
}

781 782
int blk_co_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors)
{
M
Max Reitz 已提交
783 784 785 786 787
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

788 789 790 791 792
    return bdrv_co_discard(blk->bs, sector_num, nb_sectors);
}

int blk_co_flush(BlockBackend *blk)
{
793 794 795 796
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

797 798 799
    return bdrv_co_flush(blk->bs);
}

800 801
int blk_flush(BlockBackend *blk)
{
802 803 804 805
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

806 807 808 809 810 811 812 813
    return bdrv_flush(blk->bs);
}

int blk_flush_all(void)
{
    return bdrv_flush_all();
}

814 815 816 817 818
void blk_drain(BlockBackend *blk)
{
    bdrv_drain(blk->bs);
}

819 820 821 822 823
void blk_drain_all(void)
{
    bdrv_drain_all();
}

824 825 826 827 828 829 830
void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
                      BlockdevOnError on_write_error)
{
    blk->on_read_error = on_read_error;
    blk->on_write_error = on_write_error;
}

831 832
BlockdevOnError blk_get_on_error(BlockBackend *blk, bool is_read)
{
833
    return is_read ? blk->on_read_error : blk->on_write_error;
834 835 836 837 838
}

BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read,
                                      int error)
{
839 840 841 842 843 844 845 846 847 848 849 850 851 852 853
    BlockdevOnError on_err = blk_get_on_error(blk, is_read);

    switch (on_err) {
    case BLOCKDEV_ON_ERROR_ENOSPC:
        return (error == ENOSPC) ?
               BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
    case BLOCKDEV_ON_ERROR_STOP:
        return BLOCK_ERROR_ACTION_STOP;
    case BLOCKDEV_ON_ERROR_REPORT:
        return BLOCK_ERROR_ACTION_REPORT;
    case BLOCKDEV_ON_ERROR_IGNORE:
        return BLOCK_ERROR_ACTION_IGNORE;
    default:
        abort();
    }
854 855
}

856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
static void send_qmp_error_event(BlockBackend *blk,
                                 BlockErrorAction action,
                                 bool is_read, int error)
{
    IoOperationType optype;

    optype = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
    qapi_event_send_block_io_error(blk_name(blk), optype, action,
                                   blk_iostatus_is_enabled(blk),
                                   error == ENOSPC, strerror(error),
                                   &error_abort);
}

/* This is done by device models because, while the block layer knows
 * about the error, it does not know whether an operation comes from
 * the device or the block layer (from a job, for example).
 */
873 874 875
void blk_error_action(BlockBackend *blk, BlockErrorAction action,
                      bool is_read, int error)
{
876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898
    assert(error >= 0);

    if (action == BLOCK_ERROR_ACTION_STOP) {
        /* First set the iostatus, so that "info block" returns an iostatus
         * that matches the events raised so far (an additional error iostatus
         * is fine, but not a lost one).
         */
        blk_iostatus_set_err(blk, error);

        /* Then raise the request to stop the VM and the event.
         * qemu_system_vmstop_request_prepare has two effects.  First,
         * it ensures that the STOP event always comes after the
         * BLOCK_IO_ERROR event.  Second, it ensures that even if management
         * can observe the STOP event and do a "cont" before the STOP
         * event is issued, the VM will not stop.  In this case, vm_start()
         * also ensures that the STOP/RESUME pair of events is emitted.
         */
        qemu_system_vmstop_request_prepare();
        send_qmp_error_event(blk, action, is_read, error);
        qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
    } else {
        send_qmp_error_event(blk, action, is_read, error);
    }
899 900 901 902
}

int blk_is_read_only(BlockBackend *blk)
{
903 904 905 906 907
    if (blk->bs) {
        return bdrv_is_read_only(blk->bs);
    } else {
        return blk->root_state.read_only;
    }
908 909 910 911 912 913 914 915 916
}

int blk_is_sg(BlockBackend *blk)
{
    return bdrv_is_sg(blk->bs);
}

int blk_enable_write_cache(BlockBackend *blk)
{
917 918 919 920 921
    if (blk->bs) {
        return bdrv_enable_write_cache(blk->bs);
    } else {
        return !!(blk->root_state.open_flags & BDRV_O_CACHE_WB);
    }
922 923 924 925
}

void blk_set_enable_write_cache(BlockBackend *blk, bool wce)
{
926 927 928 929 930 931 932 933 934
    if (blk->bs) {
        bdrv_set_enable_write_cache(blk->bs, wce);
    } else {
        if (wce) {
            blk->root_state.open_flags |= BDRV_O_CACHE_WB;
        } else {
            blk->root_state.open_flags &= ~BDRV_O_CACHE_WB;
        }
    }
935 936
}

937 938
void blk_invalidate_cache(BlockBackend *blk, Error **errp)
{
939 940 941 942 943
    if (!blk->bs) {
        error_setg(errp, "Device '%s' has no medium", blk->name);
        return;
    }

944 945 946
    bdrv_invalidate_cache(blk->bs, errp);
}

947
bool blk_is_inserted(BlockBackend *blk)
948
{
M
Max Reitz 已提交
949 950 951 952 953 954
    return blk->bs && bdrv_is_inserted(blk->bs);
}

bool blk_is_available(BlockBackend *blk)
{
    return blk_is_inserted(blk) && !blk_dev_is_tray_open(blk);
955 956 957 958 959 960 961 962 963 964 965 966 967 968
}

void blk_lock_medium(BlockBackend *blk, bool locked)
{
    bdrv_lock_medium(blk->bs, locked);
}

void blk_eject(BlockBackend *blk, bool eject_flag)
{
    bdrv_eject(blk->bs, eject_flag);
}

int blk_get_flags(BlockBackend *blk)
{
969 970 971 972 973
    if (blk->bs) {
        return bdrv_get_flags(blk->bs);
    } else {
        return blk->root_state.open_flags;
    }
974 975
}

976 977 978 979 980
int blk_get_max_transfer_length(BlockBackend *blk)
{
    return blk->bs->bl.max_transfer_length;
}

981 982
void blk_set_guest_block_size(BlockBackend *blk, int align)
{
983
    blk->guest_block_size = align;
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
}

void *blk_blockalign(BlockBackend *blk, size_t size)
{
    return qemu_blockalign(blk ? blk->bs : NULL, size);
}

bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
{
    return bdrv_op_is_blocked(blk->bs, op, errp);
}

void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason)
{
    bdrv_op_unblock(blk->bs, op, reason);
}

void blk_op_block_all(BlockBackend *blk, Error *reason)
{
    bdrv_op_block_all(blk->bs, reason);
}

void blk_op_unblock_all(BlockBackend *blk, Error *reason)
{
    bdrv_op_unblock_all(blk->bs, reason);
}

AioContext *blk_get_aio_context(BlockBackend *blk)
{
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
    if (blk->bs) {
        return bdrv_get_aio_context(blk->bs);
    } else {
        return qemu_get_aio_context();
    }
}

static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb)
{
    BlockBackendAIOCB *blk_acb = DO_UPCAST(BlockBackendAIOCB, common, acb);
    return blk_get_aio_context(blk_acb->blk);
1024 1025 1026 1027 1028 1029 1030
}

void blk_set_aio_context(BlockBackend *blk, AioContext *new_context)
{
    bdrv_set_aio_context(blk->bs, new_context);
}

1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048
void blk_add_aio_context_notifier(BlockBackend *blk,
        void (*attached_aio_context)(AioContext *new_context, void *opaque),
        void (*detach_aio_context)(void *opaque), void *opaque)
{
    bdrv_add_aio_context_notifier(blk->bs, attached_aio_context,
                                  detach_aio_context, opaque);
}

void blk_remove_aio_context_notifier(BlockBackend *blk,
                                     void (*attached_aio_context)(AioContext *,
                                                                  void *),
                                     void (*detach_aio_context)(void *),
                                     void *opaque)
{
    bdrv_remove_aio_context_notifier(blk->bs, attached_aio_context,
                                     detach_aio_context, opaque);
}

1049 1050 1051 1052 1053
void blk_add_close_notifier(BlockBackend *blk, Notifier *notify)
{
    bdrv_add_close_notifier(blk->bs, notify);
}

1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065
void blk_io_plug(BlockBackend *blk)
{
    bdrv_io_plug(blk->bs);
}

void blk_io_unplug(BlockBackend *blk)
{
    bdrv_io_unplug(blk->bs);
}

BlockAcctStats *blk_get_stats(BlockBackend *blk)
{
1066
    return &blk->stats;
1067 1068 1069 1070 1071 1072 1073
}

void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
                  BlockCompletionFunc *cb, void *opaque)
{
    return qemu_aio_get(aiocb_info, blk_bs(blk), cb, opaque);
}
1074 1075 1076 1077

int coroutine_fn blk_co_write_zeroes(BlockBackend *blk, int64_t sector_num,
                                     int nb_sectors, BdrvRequestFlags flags)
{
M
Max Reitz 已提交
1078 1079 1080 1081 1082
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

1083 1084 1085 1086 1087 1088
    return bdrv_co_write_zeroes(blk->bs, sector_num, nb_sectors, flags);
}

int blk_write_compressed(BlockBackend *blk, int64_t sector_num,
                         const uint8_t *buf, int nb_sectors)
{
M
Max Reitz 已提交
1089 1090 1091 1092 1093
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

1094 1095 1096 1097 1098
    return bdrv_write_compressed(blk->bs, sector_num, buf, nb_sectors);
}

int blk_truncate(BlockBackend *blk, int64_t offset)
{
1099 1100 1101 1102
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

1103 1104 1105 1106 1107
    return bdrv_truncate(blk->bs, offset);
}

int blk_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors)
{
M
Max Reitz 已提交
1108 1109 1110 1111 1112
    int ret = blk_check_request(blk, sector_num, nb_sectors);
    if (ret < 0) {
        return ret;
    }

1113 1114 1115 1116 1117 1118
    return bdrv_discard(blk->bs, sector_num, nb_sectors);
}

int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
                     int64_t pos, int size)
{
1119 1120 1121 1122
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

1123 1124 1125 1126 1127
    return bdrv_save_vmstate(blk->bs, buf, pos, size);
}

int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)
{
1128 1129 1130 1131
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

1132 1133
    return bdrv_load_vmstate(blk->bs, buf, pos, size);
}
1134 1135 1136

int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz)
{
1137 1138 1139 1140
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

1141 1142 1143 1144 1145
    return bdrv_probe_blocksizes(blk->bs, bsz);
}

int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo)
{
1146 1147 1148 1149
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

1150 1151
    return bdrv_probe_geometry(blk->bs, geo);
}
M
Max Reitz 已提交
1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182

/*
 * Updates the BlockBackendRootState object with data from the currently
 * attached BlockDriverState.
 */
void blk_update_root_state(BlockBackend *blk)
{
    assert(blk->bs);

    blk->root_state.open_flags    = blk->bs->open_flags;
    blk->root_state.read_only     = blk->bs->read_only;
    blk->root_state.detect_zeroes = blk->bs->detect_zeroes;

    if (blk->root_state.throttle_group) {
        g_free(blk->root_state.throttle_group);
        throttle_group_unref(blk->root_state.throttle_state);
    }
    if (blk->bs->throttle_state) {
        const char *name = throttle_group_get_name(blk->bs);
        blk->root_state.throttle_group = g_strdup(name);
        blk->root_state.throttle_state = throttle_group_incref(name);
    } else {
        blk->root_state.throttle_group = NULL;
        blk->root_state.throttle_state = NULL;
    }
}

BlockBackendRootState *blk_get_root_state(BlockBackend *blk)
{
    return &blk->root_state;
}