static void virtio_blk_handle_read(VirtIOBlockReq *req)
{
BlockDriverAIOCB *acb;
uint64_t sector;
sector = ldq_p(&req->out->sector);
bdrv_acct_start(req->dev->bs, &req->acct, req->qiov.size, BDRV_ACCT_READ);
if (sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
if (req->qiov.size % req->dev->conf->logical_block_size) {
virtio_blk_rw_complete(req, -EIO);
return;
}
acb = bdrv_aio_readv(req->dev->bs, sector, &req->qiov,
req->qiov.size / BDRV_SECTOR_SIZE,
virtio_blk_rw_complete, req);
if (!acb) {
virtio_blk_rw_complete(req, -EIO);
}
}
/**
* Update header in-place (does not rewrite backing filename or other strings)
*
* This function only updates known header fields in-place and does not affect
* extra data after the QED header.
*/
static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
void *opaque)
{
/* We must write full sectors for O_DIRECT but cannot necessarily generate
* the data following the header if an unrecognized compat feature is
* active. Therefore, first read the sectors containing the header, update
* them, and write back.
*/
int nsectors = (sizeof(QEDHeader) + BDRV_SECTOR_SIZE - 1) /
BDRV_SECTOR_SIZE;
size_t len = nsectors * BDRV_SECTOR_SIZE;
QEDWriteHeaderCB *write_header_cb = gencb_alloc(sizeof(*write_header_cb),
cb, opaque);
write_header_cb->s = s;
write_header_cb->nsectors = nsectors;
write_header_cb->buf = qemu_blockalign(s->bs, len);
write_header_cb->iov.iov_base = write_header_cb->buf;
write_header_cb->iov.iov_len = len;
qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1);
bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
qed_write_header_read_cb, write_header_cb);
}
/* This is where we get a request from a caller to read something */
static BlockDriverAIOCB *tar_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVTarState *s = bs->opaque;
SparseCache *sparse;
int64_t sec_file = sector_num + s->file_sec;
int64_t start = sector_num * SECTOR_SIZE;
int64_t end = start + (nb_sectors * SECTOR_SIZE);
int i;
TarAIOCB *acb;
for (i = 0; i < s->sparse_num; i++) {
sparse = &s->sparse[i];
if (sparse->start > end) {
/* We expect the cache to be start increasing */
break;
} else if ((sparse->start < start) && (sparse->end <= start)) {
/* sparse before our offset */
sec_file -= (sparse->end - sparse->start) / SECTOR_SIZE;
} else if ((sparse->start <= start) && (sparse->end >= end)) {
/* all our sectors are sparse */
char *buf = g_malloc0(nb_sectors * SECTOR_SIZE);
acb = qemu_aio_get(&tar_aiocb_info, bs, cb, opaque);
qemu_iovec_from_buf(qiov, 0, buf, nb_sectors * SECTOR_SIZE);
g_free(buf);
acb->bh = qemu_bh_new(tar_sparse_cb, acb);
qemu_bh_schedule(acb->bh);
return &acb->common;
} else if (((sparse->start >= start) && (sparse->start < end)) ||
((sparse->end >= start) && (sparse->end < end))) {
/* we're semi-sparse (worst case) */
/* let's go synchronous and read all sectors individually */
char *buf = g_malloc(nb_sectors * SECTOR_SIZE);
uint64_t offs;
for (offs = 0; offs < (nb_sectors * SECTOR_SIZE);
offs += SECTOR_SIZE) {
bdrv_pread(bs, (sector_num * SECTOR_SIZE) + offs,
buf + offs, SECTOR_SIZE);
}
qemu_iovec_from_buf(qiov, 0, buf, nb_sectors * SECTOR_SIZE);
acb = qemu_aio_get(&tar_aiocb_info, bs, cb, opaque);
acb->bh = qemu_bh_new(tar_sparse_cb, acb);
qemu_bh_schedule(acb->bh);
return &acb->common;
}
}
return bdrv_aio_readv(s->hd, sec_file, qiov, nb_sectors,
cb, opaque);
}
static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
nb_sectors, cb, opaque);
acb->verify = blkverify_verify_readv;
acb->buf = qemu_blockalign(bs->file, qiov->size);
qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
blkverify_aio_cb, acb);
bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
blkverify_aio_cb, acb);
return &acb->common;
}
static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
{
struct XenBlkDev *blkdev = ioreq->blkdev;
if (ioreq->req.nr_segments && ioreq_map(ioreq) == -1) {
goto err_no_map;
}
ioreq->aio_inflight++;
if (ioreq->presync) {
bdrv_flush(blkdev->bs); /* FIXME: aio_flush() ??? */
}
switch (ioreq->req.operation) {
case BLKIF_OP_READ:
bdrv_acct_start(blkdev->bs, &ioreq->acct, ioreq->v.size, BDRV_ACCT_READ);
ioreq->aio_inflight++;
bdrv_aio_readv(blkdev->bs, ioreq->start / BLOCK_SIZE,
&ioreq->v, ioreq->v.size / BLOCK_SIZE,
qemu_aio_complete, ioreq);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_WRITE_BARRIER:
if (!ioreq->req.nr_segments) {
break;
}
bdrv_acct_start(blkdev->bs, &ioreq->acct, ioreq->v.size, BDRV_ACCT_WRITE);
ioreq->aio_inflight++;
bdrv_aio_writev(blkdev->bs, ioreq->start / BLOCK_SIZE,
&ioreq->v, ioreq->v.size / BLOCK_SIZE,
qemu_aio_complete, ioreq);
break;
default:
/* unknown operation (shouldn't happen -- parse catches this) */
goto err;
}
if (ioreq->postsync) {
bdrv_flush(blkdev->bs); /* FIXME: aio_flush() ??? */
}
qemu_aio_complete(ioreq, 0);
return 0;
err:
ioreq_unmap(ioreq);
err_no_map:
ioreq_finish(ioreq);
ioreq->status = BLKIF_RSP_ERROR;
return -1;
}
static void dma_bdrv_cb(void *opaque, int ret)
{
DMAAIOCB *dbs = (DMAAIOCB *)opaque;
target_phys_addr_t cur_addr, cur_len;
void *mem;
dbs->acb = NULL;
dbs->sector_num += dbs->iov.size / 512;
dma_bdrv_unmap(dbs);
qemu_iovec_reset(&dbs->iov);
if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
dbs->common.cb(dbs->common.opaque, ret);
qemu_iovec_destroy(&dbs->iov);
qemu_aio_release(dbs);
return;
}
while (dbs->sg_cur_index < dbs->sg->nsg) {
cur_addr = dbs->sg->sg[dbs->sg_cur_index].base + dbs->sg_cur_byte;
cur_len = dbs->sg->sg[dbs->sg_cur_index].len - dbs->sg_cur_byte;
mem = cpu_physical_memory_map(cur_addr, &cur_len, !dbs->is_write);
if (!mem)
break;
qemu_iovec_add(&dbs->iov, mem, cur_len);
dbs->sg_cur_byte += cur_len;
if (dbs->sg_cur_byte == dbs->sg->sg[dbs->sg_cur_index].len) {
dbs->sg_cur_byte = 0;
++dbs->sg_cur_index;
}
}
if (dbs->iov.size == 0) {
cpu_register_map_client(dbs, continue_after_map_failure);
return;
}
if (dbs->is_write) {
dbs->acb = bdrv_aio_writev(dbs->bs, dbs->sector_num, &dbs->iov,
dbs->iov.size / 512, dma_bdrv_cb, dbs);
} else {
dbs->acb = bdrv_aio_readv(dbs->bs, dbs->sector_num, &dbs->iov,
dbs->iov.size / 512, dma_bdrv_cb, dbs);
}
if (!dbs->acb) {
dma_bdrv_unmap(dbs);
qemu_iovec_destroy(&dbs->iov);
return;
}
}
static void compare_full_images_cb (void *opaque, int ret)
{
CompareFullCB *cf = opaque;
if (ret) {
/* Failed. Retry the operation. */
bdrv_aio_readv (bs, cf->sector_num, &cf->qiov, cf->nb_sectors,
compare_full_images_cb, cf);
return;
}
truth_io (cf->truth_buf, cf->sector_num, cf->nb_sectors, TRUE);
verify (cf->truth_buf, cf->iov.iov_base, cf->sector_num, cf->nb_sectors);
cf->sector_num += cf->nb_sectors;
if (cf->sector_num >= total_sectors) {
/* Finished. */
free (cf->truth_buf);
qemu_vfree (cf->iov.iov_base);
g_free(cf);
return;
}
/* Read more data to compare. */
if (cf->sector_num + cf->max_nb_sectors > total_sectors) {
cf->nb_sectors = total_sectors - cf->sector_num;
} else {
cf->nb_sectors = cf->max_nb_sectors;
}
cf->iov.iov_len = cf->nb_sectors * 512;
qemu_iovec_init_external (&cf->qiov, &cf->iov, 1);
if (!bdrv_aio_readv (bs, cf->sector_num, &cf->qiov,
cf->nb_sectors, compare_full_images_cb, cf)) {
die ("bdrv_aio_readv\n");
}
}
static void virtio_blk_handle_read(VirtIOBlockReq *req)
{
BlockDriverAIOCB *acb;
if (req->out->sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
acb = bdrv_aio_readv(req->dev->bs, req->out->sector, &req->qiov,
req->qiov.size / BDRV_SECTOR_SIZE,
virtio_blk_rw_complete, req);
if (!acb) {
virtio_blk_rw_complete(req, -EIO);
}
}
static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
BlockDriverCompletionFunc *cb, void *opaque)
{
QEDReadTableCB *read_table_cb = gencb_alloc(sizeof(*read_table_cb),
cb, opaque);
QEMUIOVector *qiov = &read_table_cb->qiov;
trace_qed_read_table(s, offset, table);
read_table_cb->s = s;
read_table_cb->table = table;
read_table_cb->iov.iov_base = table->offsets,
read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size,
qemu_iovec_init_external(qiov, &read_table_cb->iov, 1);
bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov,
qiov->size / BDRV_SECTOR_SIZE,
qed_read_table_cb, read_table_cb);
}
static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
{
struct XenBlkDev *blkdev = ioreq->blkdev;
if (ioreq_map(ioreq) == -1)
goto err;
ioreq->aio_inflight++;
if (ioreq->presync)
bdrv_flush(blkdev->bs); /* FIXME: aio_flush() ??? */
switch (ioreq->req.operation) {
case BLKIF_OP_READ:
ioreq->aio_inflight++;
bdrv_aio_readv(blkdev->bs, ioreq->start / BLOCK_SIZE,
&ioreq->v, ioreq->v.size / BLOCK_SIZE,
qemu_aio_complete, ioreq);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_WRITE_BARRIER:
ioreq->aio_inflight++;
bdrv_aio_writev(blkdev->bs, ioreq->start / BLOCK_SIZE,
&ioreq->v, ioreq->v.size / BLOCK_SIZE,
qemu_aio_complete, ioreq);
break;
default:
/* unknown operation (shouldn't happen -- parse catches this) */
goto err;
}
if (ioreq->postsync)
bdrv_flush(blkdev->bs); /* FIXME: aio_flush() ??? */
qemu_aio_complete(ioreq, 0);
return 0;
err:
ioreq->status = BLKIF_RSP_ERROR;
return -1;
}
static void virtio_blk_handle_read(VirtIOBlockReq *req)
{
uint64_t sector;
sector = virtio_ldq_p(VIRTIO_DEVICE(req->dev), &req->out.sector);
bdrv_acct_start(req->dev->bs, &req->acct, req->qiov.size, BDRV_ACCT_READ);
trace_virtio_blk_handle_read(req, sector, req->qiov.size / 512);
if (sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
if (req->qiov.size % req->dev->conf->logical_block_size) {
virtio_blk_rw_complete(req, -EIO);
return;
}
bdrv_aio_readv(req->dev->bs, sector, &req->qiov,
req->qiov.size / BDRV_SECTOR_SIZE,
virtio_blk_rw_complete, req);
}
static int compare_full_images (void)
{
CompareFullCB *cf;
int old_copy_on_read = FALSE;
printf ("Performing a full comparison of the truth image and "
"the test image...\n");
if (!strncmp (bs->drv->format_name, "fvd", 3)) {
/* Disable copy-on-read when scanning through the entire image. */
old_copy_on_read = fvd_get_copy_on_read (bs);
fvd_set_copy_on_read (bs, FALSE);
}
cf = g_malloc(sizeof(CompareFullCB));
cf->max_nb_sectors = 1048576L / 512;
cf->nb_sectors = MIN (cf->max_nb_sectors, total_sectors);
if (posix_memalign ((void **) &cf->truth_buf, 512,
cf->max_nb_sectors * 512) != 0) {
die ("posix_memalign");
}
cf->iov.iov_base = qemu_blockalign (bs, cf->max_nb_sectors * 512);
cf->iov.iov_len = cf->nb_sectors * 512;
cf->sector_num = 0;
qemu_iovec_init_external (&cf->qiov, &cf->iov, 1);
if (!bdrv_aio_readv (bs, cf->sector_num, &cf->qiov,
cf->nb_sectors, compare_full_images_cb, cf)) {
die ("bdrv_aio_readv\n");
}
sim_all_tasks ();
if (!strncmp (bs->drv->format_name, "fvd", 3)) {
fvd_set_copy_on_read (bs, old_copy_on_read);
}
return 0;
}
static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
}
static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
{
BlockDriverState *source = s->common.bs;
int nb_sectors, sectors_per_chunk, nb_chunks;
int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
uint64_t delay_ns = 0;
MirrorOp *op;
int pnum;
int64_t ret;
s->sector_num = hbitmap_iter_next(&s->hbi);
if (s->sector_num < 0) {
bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
s->sector_num = hbitmap_iter_next(&s->hbi);
trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
assert(s->sector_num >= 0);
}
hbitmap_next_sector = s->sector_num;
sector_num = s->sector_num;
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
end = s->bdev_length / BDRV_SECTOR_SIZE;
/* Extend the QEMUIOVector to include all adjacent blocks that will
* be copied in this operation.
*
* We have to do this if we have no backing file yet in the destination,
* and the cluster size is very large. Then we need to do COW ourselves.
* The first time a cluster is copied, copy it entirely. Note that,
* because both the granularity and the cluster size are powers of two,
* the number of sectors to copy cannot exceed one cluster.
*
* We also want to extend the QEMUIOVector to include more adjacent
* dirty blocks if possible, to limit the number of I/O operations and
* run efficiently even with a small granularity.
*/
nb_chunks = 0;
nb_sectors = 0;
next_sector = sector_num;
next_chunk = sector_num / sectors_per_chunk;
/* Wait for I/O to this cluster (from a previous iteration) to be done. */
while (test_bit(next_chunk, s->in_flight_bitmap)) {
trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
}
do {
int added_sectors, added_chunks;
if (!bdrv_get_dirty(source, s->dirty_bitmap, next_sector) ||
test_bit(next_chunk, s->in_flight_bitmap)) {
assert(nb_sectors > 0);
break;
}
added_sectors = sectors_per_chunk;
if (s->cow_bitmap && !test_bit(next_chunk, s->cow_bitmap)) {
bdrv_round_to_clusters(s->target,
next_sector, added_sectors,
&next_sector, &added_sectors);
/* On the first iteration, the rounding may make us copy
* sectors before the first dirty one.
*/
if (next_sector < sector_num) {
assert(nb_sectors == 0);
sector_num = next_sector;
next_chunk = next_sector / sectors_per_chunk;
}
}
added_sectors = MIN(added_sectors, end - (sector_num + nb_sectors));
added_chunks = (added_sectors + sectors_per_chunk - 1) / sectors_per_chunk;
/* When doing COW, it may happen that there is not enough space for
* a full cluster. Wait if that is the case.
*/
while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
}
if (s->buf_free_count < nb_chunks + added_chunks) {
trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
break;
}
if (IOV_MAX < nb_chunks + added_chunks) {
trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
break;
}
/* We have enough free space to copy these sectors. */
bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
nb_sectors += added_sectors;
nb_chunks += added_chunks;
next_sector += added_sectors;
next_chunk += added_chunks;
if (!s->synced && s->common.speed) {
delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
}
} while (delay_ns == 0 && next_sector < end);
/* Allocate a MirrorOp that is used as an AIO callback. */
op = g_new(MirrorOp, 1);
op->s = s;
op->sector_num = sector_num;
op->nb_sectors = nb_sectors;
/* Now make a QEMUIOVector taking enough granularity-sized chunks
* from s->buf_free.
*/
qemu_iovec_init(&op->qiov, nb_chunks);
next_sector = sector_num;
while (nb_chunks-- > 0) {
MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
size_t remaining = (nb_sectors * BDRV_SECTOR_SIZE) - op->qiov.size;
QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
s->buf_free_count--;
qemu_iovec_add(&op->qiov, buf, MIN(s->granularity, remaining));
/* Advance the HBitmapIter in parallel, so that we do not examine
* the same sector twice.
*/
if (next_sector > hbitmap_next_sector
&& bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
}
next_sector += sectors_per_chunk;
}
bdrv_reset_dirty_bitmap(s->dirty_bitmap, sector_num, nb_sectors);
/* Copy the dirty cluster. */
s->in_flight++;
s->sectors_in_flight += nb_sectors;
trace_mirror_one_iteration(s, sector_num, nb_sectors);
ret = bdrv_get_block_status_above(source, NULL, sector_num,
nb_sectors, &pnum);
if (ret < 0 || pnum < nb_sectors ||
(ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) {
bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
mirror_read_complete, op);
} else if (ret & BDRV_BLOCK_ZERO) {
bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors,
s->unmap ? BDRV_REQ_MAY_UNMAP : 0,
mirror_write_complete, op);
} else {
assert(!(ret & BDRV_BLOCK_DATA));
bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
mirror_write_complete, op);
}
return delay_ns;
}
static void coroutine_fn mirror_iteration(MirrorBlockJob *s)
{
BlockDriverState *source = s->common.bs;
int nb_sectors, sectors_per_chunk, nb_chunks;
int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
MirrorOp *op;
s->sector_num = hbitmap_iter_next(&s->hbi);
if (s->sector_num < 0) {
bdrv_dirty_iter_init(source, &s->hbi);
s->sector_num = hbitmap_iter_next(&s->hbi);
trace_mirror_restart_iter(s, bdrv_get_dirty_count(source));
assert(s->sector_num >= 0);
}
hbitmap_next_sector = s->sector_num;
sector_num = s->sector_num;
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
end = s->common.len >> BDRV_SECTOR_BITS;
/* Extend the QEMUIOVector to include all adjacent blocks that will
* be copied in this operation.
*
* We have to do this if we have no backing file yet in the destination,
* and the cluster size is very large. Then we need to do COW ourselves.
* The first time a cluster is copied, copy it entirely. Note that,
* because both the granularity and the cluster size are powers of two,
* the number of sectors to copy cannot exceed one cluster.
*
* We also want to extend the QEMUIOVector to include more adjacent
* dirty blocks if possible, to limit the number of I/O operations and
* run efficiently even with a small granularity.
*/
nb_chunks = 0;
nb_sectors = 0;
next_sector = sector_num;
next_chunk = sector_num / sectors_per_chunk;
/* Wait for I/O to this cluster (from a previous iteration) to be done. */
while (test_bit(next_chunk, s->in_flight_bitmap)) {
trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
qemu_coroutine_yield();
}
do {
int added_sectors, added_chunks;
if (!bdrv_get_dirty(source, next_sector) ||
test_bit(next_chunk, s->in_flight_bitmap)) {
assert(nb_sectors > 0);
break;
}
added_sectors = sectors_per_chunk;
if (s->cow_bitmap && !test_bit(next_chunk, s->cow_bitmap)) {
bdrv_round_to_clusters(s->target,
next_sector, added_sectors,
&next_sector, &added_sectors);
/* On the first iteration, the rounding may make us copy
* sectors before the first dirty one.
*/
if (next_sector < sector_num) {
assert(nb_sectors == 0);
sector_num = next_sector;
next_chunk = next_sector / sectors_per_chunk;
}
}
added_sectors = MIN(added_sectors, end - (sector_num + nb_sectors));
added_chunks = (added_sectors + sectors_per_chunk - 1) / sectors_per_chunk;
/* When doing COW, it may happen that there is not enough space for
* a full cluster. Wait if that is the case.
*/
while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
qemu_coroutine_yield();
}
if (s->buf_free_count < nb_chunks + added_chunks) {
trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
break;
}
/* We have enough free space to copy these sectors. */
bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
nb_sectors += added_sectors;
nb_chunks += added_chunks;
next_sector += added_sectors;
next_chunk += added_chunks;
} while (next_sector < end);
/* Allocate a MirrorOp that is used as an AIO callback. */
op = g_slice_new(MirrorOp);
op->s = s;
op->sector_num = sector_num;
op->nb_sectors = nb_sectors;
/* Now make a QEMUIOVector taking enough granularity-sized chunks
* from s->buf_free.
*/
qemu_iovec_init(&op->qiov, nb_chunks);
next_sector = sector_num;
while (nb_chunks-- > 0) {
MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
s->buf_free_count--;
qemu_iovec_add(&op->qiov, buf, s->granularity);
/* Advance the HBitmapIter in parallel, so that we do not examine
* the same sector twice.
*/
if (next_sector > hbitmap_next_sector && bdrv_get_dirty(source, next_sector)) {
hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
}
next_sector += sectors_per_chunk;
}
bdrv_reset_dirty(source, sector_num, nb_sectors);
/* Copy the dirty cluster. */
s->in_flight++;
trace_mirror_one_iteration(s, sector_num, nb_sectors);
bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
mirror_read_complete, op);
}
/* Return FALSE if the submitted request is cancelled. */
static int submit_rand_io (RandomIO * r)
{
BlockDriverAIOCB *acb = NULL;
QDEBUG ("TESTER %03d: %s test%" PRIX64 " sector_num=%" PRId64
" nb_sectors=%d niov=%d\n", r->tester, op_type_str[r->type],
r->uuid, r->sector_num, r->nb_sectors, r->qiov.niov);
printf ("TESTER %03d: %s sector_num=%" PRId64 " nb_sectors=%d niov=%d\n",
r->tester, op_type_str[r->type], r->sector_num, r->nb_sectors,
r->qiov.niov);
int ret;
if (fail_prob <= 0) {
ret = 0;
} else if (random () / (double) RAND_MAX <= fail_prob) {
ret = -EIO;
} else {
ret = 0;
}
/* This affects whether this request will fail or not. */
sim_set_disk_io_return_code (ret);
switch (r->type) {
case OP_READ:
if (!(acb = bdrv_aio_readv (bs, r->sector_num, &r->qiov, r->nb_sectors,
rand_io_cb, r))) {
die ("bdrv_aio_readv\n");
}
break;
case OP_WRITE:
if (!(acb = bdrv_aio_writev (bs, r->sector_num, &r->qiov, r->nb_sectors,
rand_io_cb, r))) {
die ("bdrv_aio_writev\n");
}
break;
case OP_FLUSH:
if (!(acb = bdrv_aio_flush (bs, rand_io_cb, r))) {
die ("bdrv_aio_flush\n");
}
break;
case OP_NULL:
die ("OP_NULL");
break;
}
sim_set_disk_io_return_code (0); /* Reset to no failure state. */
if (r->allow_cancel && cancel_prob > 0 &&
random () / (double) RAND_MAX <= cancel_prob) {
QDEBUG ("TESTER %03d: cancel %s test%" PRIX64 " sector_num=%" PRId64
" nb_sectors=%d niov=%d\n", r->tester, op_type_str[r->type],
r->uuid, r->sector_num, r->nb_sectors, r->qiov.niov);
printf ("TESTER %03d: cancel %s sector_num=%" PRId64
" nb_sectors=%d niov=%d\n", r->tester, op_type_str[r->type],
r->sector_num, r->nb_sectors, r->qiov.niov);
bdrv_aio_cancel (acb);
return FALSE;
} else {
return TRUE;
}
}
