static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
int start, int num_reqs, int niov)
{
QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
int64_t sector_num = mrb->reqs[start]->sector_num;
bool is_write = mrb->is_write;
if (num_reqs > 1) {
int i;
struct iovec *tmp_iov = qiov->iov;
int tmp_niov = qiov->niov;
/* mrb->reqs[start]->qiov was initialized from external so we can't
* modify it here. We need to initialize it locally and then add the
* external iovecs. */
qemu_iovec_init(qiov, niov);
for (i = 0; i < tmp_niov; i++) {
qemu_iovec_add(qiov, tmp_iov[i].iov_base, tmp_iov[i].iov_len);
}
for (i = start + 1; i < start + num_reqs; i++) {
qemu_iovec_concat(qiov, &mrb->reqs[i]->qiov, 0,
mrb->reqs[i]->qiov.size);
mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
}
trace_virtio_blk_submit_multireq(VIRTIO_DEVICE(mrb->reqs[start]->dev),
mrb, start, num_reqs,
sector_num << BDRV_SECTOR_BITS,
qiov->size, is_write);
block_acct_merge_done(blk_get_stats(blk),
is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ,
num_reqs - 1);
}
if (is_write) {
blk_aio_pwritev(blk, sector_num << BDRV_SECTOR_BITS, qiov, 0,
virtio_blk_rw_complete, mrb->reqs[start]);
} else {
blk_aio_preadv(blk, sector_num << BDRV_SECTOR_BITS, qiov, 0,
virtio_blk_rw_complete, mrb->reqs[start]);
}
}
/* Submit async read while handling COW.
* Returns: The number of bytes copied after and including offset,
* excluding any bytes copied prior to offset due to alignment.
* This will be @bytes if no alignment is necessary, or
* (new_end - offset) if tail is rounded up or down due to
* alignment or buffer limit.
*/
static uint64_t mirror_do_read(MirrorBlockJob *s, int64_t offset,
uint64_t bytes)
{
BlockBackend *source = s->common.blk;
int nb_chunks;
uint64_t ret;
MirrorOp *op;
uint64_t max_bytes;
max_bytes = s->granularity * s->max_iov;
/* We can only handle as much as buf_size at a time. */
bytes = MIN(s->buf_size, MIN(max_bytes, bytes));
assert(bytes);
assert(bytes < BDRV_REQUEST_MAX_BYTES);
ret = bytes;
if (s->cow_bitmap) {
ret += mirror_cow_align(s, &offset, &bytes);
}
assert(bytes <= s->buf_size);
/* The offset is granularity-aligned because:
* 1) Caller passes in aligned values;
* 2) mirror_cow_align is used only when target cluster is larger. */
assert(QEMU_IS_ALIGNED(offset, s->granularity));
/* The range is sector-aligned, since bdrv_getlength() rounds up. */
assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));
nb_chunks = DIV_ROUND_UP(bytes, s->granularity);
while (s->buf_free_count < nb_chunks) {
trace_mirror_yield_in_flight(s, offset, s->in_flight);
mirror_wait_for_io(s);
}
/* Allocate a MirrorOp that is used as an AIO callback. */
op = g_new(MirrorOp, 1);
op->s = s;
op->offset = offset;
op->bytes = bytes;
/* Now make a QEMUIOVector taking enough granularity-sized chunks
* from s->buf_free.
*/
qemu_iovec_init(&op->qiov, nb_chunks);
while (nb_chunks-- > 0) {
MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
size_t remaining = bytes - op->qiov.size;
QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
s->buf_free_count--;
qemu_iovec_add(&op->qiov, buf, MIN(s->granularity, remaining));
}
/* Copy the dirty cluster. */
s->in_flight++;
s->bytes_in_flight += bytes;
trace_mirror_one_iteration(s, offset, bytes);
blk_aio_preadv(source, offset, &op->qiov, 0, mirror_read_complete, op);
return ret;
}
static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
{
struct XenBlkDev *blkdev = ioreq->blkdev;
ioreq->buf = qemu_memalign(XC_PAGE_SIZE, ioreq->size);
if (ioreq->req.nr_segments &&
(ioreq->req.operation == BLKIF_OP_WRITE ||
ioreq->req.operation == BLKIF_OP_FLUSH_DISKCACHE) &&
ioreq_grant_copy(ioreq)) {
qemu_vfree(ioreq->buf);
goto err;
}
ioreq->aio_inflight++;
if (ioreq->presync) {
blk_aio_flush(ioreq->blkdev->blk, qemu_aio_complete, ioreq);
return 0;
}
switch (ioreq->req.operation) {
case BLKIF_OP_READ:
qemu_iovec_add(&ioreq->v, ioreq->buf, ioreq->size);
block_acct_start(blk_get_stats(blkdev->blk), &ioreq->acct,
ioreq->v.size, BLOCK_ACCT_READ);
ioreq->aio_inflight++;
blk_aio_preadv(blkdev->blk, ioreq->start, &ioreq->v, 0,
qemu_aio_complete, ioreq);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!ioreq->req.nr_segments) {
break;
}
qemu_iovec_add(&ioreq->v, ioreq->buf, ioreq->size);
block_acct_start(blk_get_stats(blkdev->blk), &ioreq->acct,
ioreq->v.size,
ioreq->req.operation == BLKIF_OP_WRITE ?
BLOCK_ACCT_WRITE : BLOCK_ACCT_FLUSH);
ioreq->aio_inflight++;
blk_aio_pwritev(blkdev->blk, ioreq->start, &ioreq->v, 0,
qemu_aio_complete, ioreq);
break;
case BLKIF_OP_DISCARD:
{
struct blkif_request_discard *req = (void *)&ioreq->req;
if (!blk_split_discard(ioreq, req->sector_number, req->nr_sectors)) {
goto err;
}
break;
}
default:
/* unknown operation (shouldn't happen -- parse catches this) */
goto err;
}
qemu_aio_complete(ioreq, 0);
return 0;
err:
ioreq_finish(ioreq);
ioreq->status = BLKIF_RSP_ERROR;
return -1;
}
static int xen_block_do_aio(XenBlockRequest *request)
{
XenBlockDataPlane *dataplane = request->dataplane;
if (request->req.nr_segments &&
(request->req.operation == BLKIF_OP_WRITE ||
request->req.operation == BLKIF_OP_FLUSH_DISKCACHE) &&
xen_block_copy_request(request)) {
goto err;
}
request->aio_inflight++;
if (request->presync) {
blk_aio_flush(request->dataplane->blk, xen_block_complete_aio,
request);
return 0;
}
switch (request->req.operation) {
case BLKIF_OP_READ:
qemu_iovec_add(&request->v, request->buf, request->size);
block_acct_start(blk_get_stats(dataplane->blk), &request->acct,
request->v.size, BLOCK_ACCT_READ);
request->aio_inflight++;
blk_aio_preadv(dataplane->blk, request->start, &request->v, 0,
xen_block_complete_aio, request);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!request->req.nr_segments) {
break;
}
qemu_iovec_add(&request->v, request->buf, request->size);
block_acct_start(blk_get_stats(dataplane->blk), &request->acct,
request->v.size,
request->req.operation == BLKIF_OP_WRITE ?
BLOCK_ACCT_WRITE : BLOCK_ACCT_FLUSH);
request->aio_inflight++;
blk_aio_pwritev(dataplane->blk, request->start, &request->v, 0,
xen_block_complete_aio, request);
break;
case BLKIF_OP_DISCARD:
{
struct blkif_request_discard *req = (void *)&request->req;
if (!xen_block_split_discard(request, req->sector_number,
req->nr_sectors)) {
goto err;
}
break;
}
default:
/* unknown operation (shouldn't happen -- parse catches this) */
goto err;
}
xen_block_complete_aio(request, 0);
return 0;
err:
xen_block_finish_request(request);
request->status = BLKIF_RSP_ERROR;
return -1;
}
