-static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset,
- QEMUIOVector *qiov, bool is_write,
- BdrvRequestFlags flags)
-{
- Coroutine *co;
- RwCo rwco = {
- .bs = bs,
- .offset = offset,
- .qiov = qiov,
- .is_write = is_write,
- .ret = NOT_DONE,
- .flags = flags,
- };
-
- /**
- * In sync call context, when the vcpu is blocked, this throttling timer
- * will not fire; so the I/O throttling function has to be disabled here
- * if it has been enabled.
- */
- if (bs->io_limits_enabled) {
- fprintf(stderr, "Disabling I/O throttling on '%s' due "
- "to synchronous I/O.\n", bdrv_get_device_name(bs));
- bdrv_io_limits_disable(bs);
- }
-
- if (qemu_in_coroutine()) {
- /* Fast-path if already in coroutine context */
- bdrv_rw_co_entry(&rwco);
- } else {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- co = qemu_coroutine_create(bdrv_rw_co_entry);
- qemu_coroutine_enter(co, &rwco);
- while (rwco.ret == NOT_DONE) {
- aio_poll(aio_context, true);
- }
- }
- return rwco.ret;
-}
-
-/*
- * Process a synchronous request using coroutines
- */
-static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
- int nb_sectors, bool is_write, BdrvRequestFlags flags)
-{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
- };
-
- if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_prwv_co(bs, sector_num << BDRV_SECTOR_BITS,
- &qiov, is_write, flags);
-}
-
-/* return < 0 if error. See bdrv_write() for the return codes */
-int bdrv_read(BlockDriverState *bs, int64_t sector_num,
- uint8_t *buf, int nb_sectors)
-{
- return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false, 0);
-}
-
-/* Just like bdrv_read(), but with I/O throttling temporarily disabled */
-int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
- uint8_t *buf, int nb_sectors)
-{
- bool enabled;
- int ret;
-
- enabled = bs->io_limits_enabled;
- bs->io_limits_enabled = false;
- ret = bdrv_read(bs, sector_num, buf, nb_sectors);
- bs->io_limits_enabled = enabled;
- return ret;
-}
-
-/* Return < 0 if error. Important errors are:
- -EIO generic I/O error (may happen for all errors)
- -ENOMEDIUM No media inserted.
- -EINVAL Invalid sector number or nb_sectors
- -EACCES Trying to write a read-only device
-*/
-int bdrv_write(BlockDriverState *bs, int64_t sector_num,
- const uint8_t *buf, int nb_sectors)
-{
- return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true, 0);
-}
-
-int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, BdrvRequestFlags flags)
-{
- return bdrv_rw_co(bs, sector_num, NULL, nb_sectors, true,
- BDRV_REQ_ZERO_WRITE | flags);
-}
-
-/*
- * Completely zero out a block device with the help of bdrv_write_zeroes.
- * The operation is sped up by checking the block status and only writing
- * zeroes to the device if they currently do not return zeroes. Optional
- * flags are passed through to bdrv_write_zeroes (e.g. BDRV_REQ_MAY_UNMAP).
- *
- * Returns < 0 on error, 0 on success. For error codes see bdrv_write().
- */
-int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
-{
- int64_t target_sectors, ret, nb_sectors, sector_num = 0;
- int n;
-
- target_sectors = bdrv_nb_sectors(bs);
- if (target_sectors < 0) {
- return target_sectors;
- }
-
- for (;;) {
- nb_sectors = target_sectors - sector_num;
- if (nb_sectors <= 0) {
- return 0;
- }
- if (nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
- nb_sectors = INT_MAX / BDRV_SECTOR_SIZE;
- }
- ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
- if (ret < 0) {
- error_report("error getting block status at sector %" PRId64 ": %s",
- sector_num, strerror(-ret));
- return ret;
- }
- if (ret & BDRV_BLOCK_ZERO) {
- sector_num += n;
- continue;
- }
- ret = bdrv_write_zeroes(bs, sector_num, n, flags);
- if (ret < 0) {
- error_report("error writing zeroes at sector %" PRId64 ": %s",
- sector_num, strerror(-ret));
- return ret;
- }
- sector_num += n;
- }
-}
-
-int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes)
-{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = bytes,
- };
- int ret;
-
- if (bytes < 0) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- ret = bdrv_prwv_co(bs, offset, &qiov, false, 0);
- if (ret < 0) {
- return ret;
- }
-
- return bytes;
-}
-
-int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
-{
- int ret;
-
- ret = bdrv_prwv_co(bs, offset, qiov, true, 0);
- if (ret < 0) {
- return ret;
- }
-
- return qiov->size;
-}
-
-int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
- const void *buf, int bytes)
-{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *) buf,
- .iov_len = bytes,
- };
-
- if (bytes < 0) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_pwritev(bs, offset, &qiov);
-}
-
-/*
- * Writes to the file and ensures that no writes are reordered across this
- * request (acts as a barrier)
- *
- * Returns 0 on success, -errno in error cases.
- */
-int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
- const void *buf, int count)
-{
- int ret;
-
- ret = bdrv_pwrite(bs, offset, buf, count);
- if (ret < 0) {
- return ret;
- }
-
- /* No flush needed for cache modes that already do it */
- if (bs->enable_write_cache) {
- bdrv_flush(bs);
- }
-
- return 0;
-}
-
-static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
- /* Perform I/O through a temporary buffer so that users who scribble over
- * their read buffer while the operation is in progress do not end up
- * modifying the image file. This is critical for zero-copy guest I/O
- * where anything might happen inside guest memory.
- */
- void *bounce_buffer;
-
- BlockDriver *drv = bs->drv;
- struct iovec iov;
- QEMUIOVector bounce_qiov;
- int64_t cluster_sector_num;
- int cluster_nb_sectors;
- size_t skip_bytes;
- int ret;
-
- /* Cover entire cluster so no additional backing file I/O is required when
- * allocating cluster in the image file.
- */
- bdrv_round_to_clusters(bs, sector_num, nb_sectors,
- &cluster_sector_num, &cluster_nb_sectors);
-
- trace_bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors,
- cluster_sector_num, cluster_nb_sectors);
-
- iov.iov_len = cluster_nb_sectors * BDRV_SECTOR_SIZE;
- iov.iov_base = bounce_buffer = qemu_try_blockalign(bs, iov.iov_len);
- if (bounce_buffer == NULL) {
- ret = -ENOMEM;
- goto err;
- }
-
- qemu_iovec_init_external(&bounce_qiov, &iov, 1);
-
- ret = drv->bdrv_co_readv(bs, cluster_sector_num, cluster_nb_sectors,
- &bounce_qiov);
- if (ret < 0) {
- goto err;
- }
-
- if (drv->bdrv_co_write_zeroes &&
- buffer_is_zero(bounce_buffer, iov.iov_len)) {
- ret = bdrv_co_do_write_zeroes(bs, cluster_sector_num,
- cluster_nb_sectors, 0);
- } else {
- /* This does not change the data on the disk, it is not necessary
- * to flush even in cache=writethrough mode.
- */
- ret = drv->bdrv_co_writev(bs, cluster_sector_num, cluster_nb_sectors,
- &bounce_qiov);
- }
-
- if (ret < 0) {
- /* It might be okay to ignore write errors for guest requests. If this
- * is a deliberate copy-on-read then we don't want to ignore the error.
- * Simply report it in all cases.
- */
- goto err;
- }
-
- skip_bytes = (sector_num - cluster_sector_num) * BDRV_SECTOR_SIZE;
- qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes,
- nb_sectors * BDRV_SECTOR_SIZE);
-
-err:
- qemu_vfree(bounce_buffer);
- return ret;
-}
-
-/*
- * Forwards an already correctly aligned request to the BlockDriver. This
- * handles copy on read and zeroing after EOF; any other features must be
- * implemented by the caller.
- */
-static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
- BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
- int64_t align, QEMUIOVector *qiov, int flags)
-{
- BlockDriver *drv = bs->drv;
- int ret;
-
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert(!qiov || bytes == qiov->size);
-
- /* Handle Copy on Read and associated serialisation */
- if (flags & BDRV_REQ_COPY_ON_READ) {
- /* If we touch the same cluster it counts as an overlap. This
- * guarantees that allocating writes will be serialized and not race
- * with each other for the same cluster. For example, in copy-on-read
- * it ensures that the CoR read and write operations are atomic and
- * guest writes cannot interleave between them. */
- mark_request_serialising(req, bdrv_get_cluster_size(bs));
- }
-
- wait_serialising_requests(req);
-
- if (flags & BDRV_REQ_COPY_ON_READ) {
- int pnum;
-
- ret = bdrv_is_allocated(bs, sector_num, nb_sectors, &pnum);
- if (ret < 0) {
- goto out;
- }
-
- if (!ret || pnum != nb_sectors) {
- ret = bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors, qiov);
- goto out;
- }
- }
-
- /* Forward the request to the BlockDriver */
- if (!(bs->zero_beyond_eof && bs->growable)) {
- ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
- } else {
- /* Read zeros after EOF of growable BDSes */
- int64_t total_sectors, max_nb_sectors;
-
- total_sectors = bdrv_nb_sectors(bs);
- if (total_sectors < 0) {
- ret = total_sectors;
- goto out;
- }
-
- max_nb_sectors = ROUND_UP(MAX(0, total_sectors - sector_num),
- align >> BDRV_SECTOR_BITS);
- if (nb_sectors < max_nb_sectors) {
- ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
- } else if (max_nb_sectors > 0) {
- QEMUIOVector local_qiov;
-
- qemu_iovec_init(&local_qiov, qiov->niov);
- qemu_iovec_concat(&local_qiov, qiov, 0,
- max_nb_sectors * BDRV_SECTOR_SIZE);
-
- ret = drv->bdrv_co_readv(bs, sector_num, max_nb_sectors,
- &local_qiov);
-
- qemu_iovec_destroy(&local_qiov);
- } else {
- ret = 0;
- }
-
- /* Reading beyond end of file is supposed to produce zeroes */
- if (ret == 0 && total_sectors < sector_num + nb_sectors) {
- uint64_t offset = MAX(0, total_sectors - sector_num);
- uint64_t bytes = (sector_num + nb_sectors - offset) *
- BDRV_SECTOR_SIZE;
- qemu_iovec_memset(qiov, offset * BDRV_SECTOR_SIZE, 0, bytes);
- }
- }
-
-out:
- return ret;
-}
-
-/*
- * Handle a read request in coroutine context
- */
-static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- BlockDriver *drv = bs->drv;
- BdrvTrackedRequest req;
-
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
- uint8_t *head_buf = NULL;
- uint8_t *tail_buf = NULL;
- QEMUIOVector local_qiov;
- bool use_local_qiov = false;
- int ret;
-
- if (!drv) {
- return -ENOMEDIUM;
- }
- if (bdrv_check_byte_request(bs, offset, bytes)) {
- return -EIO;
- }
-
- if (bs->copy_on_read) {
- flags |= BDRV_REQ_COPY_ON_READ;
- }
-
- /* throttling disk I/O */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_intercept(bs, bytes, false);
- }
-
- /* Align read if necessary by padding qiov */
- if (offset & (align - 1)) {
- head_buf = qemu_blockalign(bs, align);
- qemu_iovec_init(&local_qiov, qiov->niov + 2);
- qemu_iovec_add(&local_qiov, head_buf, offset & (align - 1));
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
-
- bytes += offset & (align - 1);
- offset = offset & ~(align - 1);
- }
-
- if ((offset + bytes) & (align - 1)) {
- if (!use_local_qiov) {
- qemu_iovec_init(&local_qiov, qiov->niov + 1);
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
- }
- tail_buf = qemu_blockalign(bs, align);
- qemu_iovec_add(&local_qiov, tail_buf,
- align - ((offset + bytes) & (align - 1)));
-
- bytes = ROUND_UP(bytes, align);
- }
-
- tracked_request_begin(&req, bs, offset, bytes, false);
- ret = bdrv_aligned_preadv(bs, &req, offset, bytes, align,
- use_local_qiov ? &local_qiov : qiov,
- flags);
- tracked_request_end(&req);
-
- if (use_local_qiov) {
- qemu_iovec_destroy(&local_qiov);
- qemu_vfree(head_buf);
- qemu_vfree(tail_buf);
- }
-
- return ret;
-}
-
-static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- if (nb_sectors < 0 || nb_sectors > (UINT_MAX >> BDRV_SECTOR_BITS)) {
- return -EINVAL;
- }
-
- return bdrv_co_do_preadv(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
-}
-
-int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, QEMUIOVector *qiov)
-{
- trace_bdrv_co_readv(bs, sector_num, nb_sectors);
-
- return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov, 0);
-}
-
-int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
- trace_bdrv_co_copy_on_readv(bs, sector_num, nb_sectors);
-
- return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov,
- BDRV_REQ_COPY_ON_READ);
-}
-
-#define MAX_WRITE_ZEROES_BOUNCE_BUFFER 32768
-
-static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
-{
- BlockDriver *drv = bs->drv;
- QEMUIOVector qiov;
- struct iovec iov = {0};
- int ret = 0;
-
- int max_write_zeroes = bs->bl.max_write_zeroes ?
- bs->bl.max_write_zeroes : INT_MAX;
-
- while (nb_sectors > 0 && !ret) {
- int num = nb_sectors;
-
- /* Align request. Block drivers can expect the "bulk" of the request
- * to be aligned.
- */
- if (bs->bl.write_zeroes_alignment
- && num > bs->bl.write_zeroes_alignment) {
- if (sector_num % bs->bl.write_zeroes_alignment != 0) {
- /* Make a small request up to the first aligned sector. */
- num = bs->bl.write_zeroes_alignment;
- num -= sector_num % bs->bl.write_zeroes_alignment;
- } else if ((sector_num + num) % bs->bl.write_zeroes_alignment != 0) {
- /* Shorten the request to the last aligned sector. num cannot
- * underflow because num > bs->bl.write_zeroes_alignment.
- */
- num -= (sector_num + num) % bs->bl.write_zeroes_alignment;
- }
- }
-
- /* limit request size */
- if (num > max_write_zeroes) {
- num = max_write_zeroes;
- }
-
- ret = -ENOTSUP;
- /* First try the efficient write zeroes operation */
- if (drv->bdrv_co_write_zeroes) {
- ret = drv->bdrv_co_write_zeroes(bs, sector_num, num, flags);
- }
-
- if (ret == -ENOTSUP) {
- /* Fall back to bounce buffer if write zeroes is unsupported */
- int max_xfer_len = MIN_NON_ZERO(bs->bl.max_transfer_length,
- MAX_WRITE_ZEROES_BOUNCE_BUFFER);
- num = MIN(num, max_xfer_len);
- iov.iov_len = num * BDRV_SECTOR_SIZE;
- if (iov.iov_base == NULL) {
- iov.iov_base = qemu_try_blockalign(bs, num * BDRV_SECTOR_SIZE);
- if (iov.iov_base == NULL) {
- ret = -ENOMEM;
- goto fail;
- }
- memset(iov.iov_base, 0, num * BDRV_SECTOR_SIZE);
- }
- qemu_iovec_init_external(&qiov, &iov, 1);
-
- ret = drv->bdrv_co_writev(bs, sector_num, num, &qiov);
-
- /* Keep bounce buffer around if it is big enough for all
- * all future requests.
- */
- if (num < max_xfer_len) {
- qemu_vfree(iov.iov_base);
- iov.iov_base = NULL;
- }
- }
-
- sector_num += num;
- nb_sectors -= num;
- }
-
-fail:
- qemu_vfree(iov.iov_base);
- return ret;
-}
-
-/*
- * Forwards an already correctly aligned write request to the BlockDriver.
- */
-static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
- BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
- QEMUIOVector *qiov, int flags)
-{
- BlockDriver *drv = bs->drv;
- bool waited;
- int ret;
-
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert(!qiov || bytes == qiov->size);
-
- waited = wait_serialising_requests(req);
- assert(!waited || !req->serialising);
- assert(req->overlap_offset <= offset);
- assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
-
- ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
-
- if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF &&
- !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_write_zeroes &&
- qemu_iovec_is_zero(qiov)) {
- flags |= BDRV_REQ_ZERO_WRITE;
- if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) {
- flags |= BDRV_REQ_MAY_UNMAP;
- }
- }
-
- if (ret < 0) {
- /* Do nothing, write notifier decided to fail this request */
- } else if (flags & BDRV_REQ_ZERO_WRITE) {
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_ZERO);
- ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors, flags);
- } else {
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV);
- ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
- }
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_DONE);
-
- if (ret == 0 && !bs->enable_write_cache) {
- ret = bdrv_co_flush(bs);
- }
-
- bdrv_set_dirty(bs, sector_num, nb_sectors);
-
- block_acct_highest_sector(&bs->stats, sector_num, nb_sectors);
-
- if (bs->growable && ret >= 0) {
- bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
- }
-
- return ret;
-}
-
-/*
- * Handle a write request in coroutine context
- */
-static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- BdrvTrackedRequest req;
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
- uint8_t *head_buf = NULL;
- uint8_t *tail_buf = NULL;
- QEMUIOVector local_qiov;
- bool use_local_qiov = false;
- int ret;
-
- if (!bs->drv) {
- return -ENOMEDIUM;
- }
- if (bs->read_only) {
- return -EACCES;
- }
- if (bdrv_check_byte_request(bs, offset, bytes)) {
- return -EIO;
- }
-
- /* throttling disk I/O */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_intercept(bs, bytes, true);
- }
-
- /*
- * Align write if necessary by performing a read-modify-write cycle.
- * Pad qiov with the read parts and be sure to have a tracked request not
- * only for bdrv_aligned_pwritev, but also for the reads of the RMW cycle.
- */
- tracked_request_begin(&req, bs, offset, bytes, true);
-
- if (offset & (align - 1)) {
- QEMUIOVector head_qiov;
- struct iovec head_iov;
-
- mark_request_serialising(&req, align);
- wait_serialising_requests(&req);
-
- head_buf = qemu_blockalign(bs, align);
- head_iov = (struct iovec) {
- .iov_base = head_buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&head_qiov, &head_iov, 1);
-
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_HEAD);
- ret = bdrv_aligned_preadv(bs, &req, offset & ~(align - 1), align,
- align, &head_qiov, 0);
- if (ret < 0) {
- goto fail;
- }
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
-
- qemu_iovec_init(&local_qiov, qiov->niov + 2);
- qemu_iovec_add(&local_qiov, head_buf, offset & (align - 1));
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
-
- bytes += offset & (align - 1);
- offset = offset & ~(align - 1);
- }
-
- if ((offset + bytes) & (align - 1)) {
- QEMUIOVector tail_qiov;
- struct iovec tail_iov;
- size_t tail_bytes;
- bool waited;
-
- mark_request_serialising(&req, align);
- waited = wait_serialising_requests(&req);
- assert(!waited || !use_local_qiov);
-
- tail_buf = qemu_blockalign(bs, align);
- tail_iov = (struct iovec) {
- .iov_base = tail_buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&tail_qiov, &tail_iov, 1);
-
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_TAIL);
- ret = bdrv_aligned_preadv(bs, &req, (offset + bytes) & ~(align - 1), align,
- align, &tail_qiov, 0);
- if (ret < 0) {
- goto fail;
- }
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
-
- if (!use_local_qiov) {
- qemu_iovec_init(&local_qiov, qiov->niov + 1);
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
- }
-
- tail_bytes = (offset + bytes) & (align - 1);
- qemu_iovec_add(&local_qiov, tail_buf + tail_bytes, align - tail_bytes);
-
- bytes = ROUND_UP(bytes, align);
- }
-
- ret = bdrv_aligned_pwritev(bs, &req, offset, bytes,
- use_local_qiov ? &local_qiov : qiov,
- flags);
-
-fail:
- tracked_request_end(&req);
-
- if (use_local_qiov) {
- qemu_iovec_destroy(&local_qiov);
- }
- qemu_vfree(head_buf);
- qemu_vfree(tail_buf);
-
- return ret;
-}
-
-static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- if (nb_sectors < 0 || nb_sectors > (INT_MAX >> BDRV_SECTOR_BITS)) {
- return -EINVAL;
- }
-
- return bdrv_co_do_pwritev(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
-}
-
-int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, QEMUIOVector *qiov)
-{
- trace_bdrv_co_writev(bs, sector_num, nb_sectors);
-
- return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov, 0);
-}
-
-int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- BdrvRequestFlags flags)
-{
- trace_bdrv_co_write_zeroes(bs, sector_num, nb_sectors, flags);
-
- if (!(bs->open_flags & BDRV_O_UNMAP)) {
- flags &= ~BDRV_REQ_MAY_UNMAP;
- }
-
- return bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
- BDRV_REQ_ZERO_WRITE | flags);
-}
-
-/**
- * Truncate file to 'offset' bytes (needed only for file protocols)
- */
-int bdrv_truncate(BlockDriverState *bs, int64_t offset)
-{
- BlockDriver *drv = bs->drv;
- int ret;
- if (!drv)
- return -ENOMEDIUM;
- if (!drv->bdrv_truncate)
- return -ENOTSUP;
- if (bs->read_only)
- return -EACCES;
-
- ret = drv->bdrv_truncate(bs, offset);
- if (ret == 0) {
- ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
- if (bs->blk) {
- blk_dev_resize_cb(bs->blk);
- }
- }
- return ret;
-}
-
-/**
- * Length of a allocated file in bytes. Sparse files are counted by actual
- * allocated space. Return < 0 if error or unknown.
- */
-int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
- if (!drv) {
- return -ENOMEDIUM;
- }
- if (drv->bdrv_get_allocated_file_size) {
- return drv->bdrv_get_allocated_file_size(bs);
- }
- if (bs->file) {
- return bdrv_get_allocated_file_size(bs->file);
- }
- return -ENOTSUP;
-}
-
-/**
- * Return number of sectors on success, -errno on error.
- */
-int64_t bdrv_nb_sectors(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
-
- if (!drv)
- return -ENOMEDIUM;
-
- if (drv->has_variable_length) {
- int ret = refresh_total_sectors(bs, bs->total_sectors);
- if (ret < 0) {
- return ret;
- }
- }
- return bs->total_sectors;
-}
-
-/**
- * Return length in bytes on success, -errno on error.
- * The length is always a multiple of BDRV_SECTOR_SIZE.
- */
-int64_t bdrv_getlength(BlockDriverState *bs)
projects / qemu.git / blobdiff