static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBlock *s = to_virtio_blk(vdev);
VirtIOBlockReq *req;
MultiReqBuffer mrb = {
.num_writes = 0,
};
while ((req = virtio_blk_get_request(s))) {
virtio_blk_handle_request(req, &mrb);
}
virtio_submit_multiwrite(s->bs, &mrb);
/*
* FIXME: Want to check for completions before returning to guest mode,
* so cached reads and writes are reported as quickly as possible. But
* that should be done in the generic block layer.
*/
}
static void virtio_blk_dma_restart_bh(void *opaque)
{
VirtIOBlock *s = opaque;
VirtIOBlockReq *req = s->rq;
MultiReqBuffer mrb = {
.num_writes = 0,
};
qemu_bh_delete(s->bh);
s->bh = NULL;
s->rq = NULL;
while (req) {
virtio_blk_handle_request(req, &mrb);
req = req->next;
}
virtio_submit_multiwrite(s->bs, &mrb);
}
static void virtio_blk_dma_restart_cb(void *opaque, int running,
RunState state)
{
VirtIOBlock *s = opaque;
if (!running)
return;
if (!s->bh) {
s->bh = qemu_bh_new(virtio_blk_dma_restart_bh, s);
qemu_bh_schedule(s->bh);
}
}
static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
BlockRequest *blkreq;
uint64_t sector;
sector = ldq_p(&req->out->sector);
trace_virtio_blk_handle_write(req, sector, req->qiov.size / 512);
if (sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
if (mrb->num_writes == 32) {
virtio_submit_multiwrite(req->dev->bs, mrb);
}
blkreq = &mrb->blkreq[mrb->num_writes];
blkreq->sector = sector;
blkreq->nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
blkreq->qiov = &req->qiov;
blkreq->cb = virtio_blk_rw_complete;
blkreq->opaque = req;
blkreq->error = 0;
mrb->num_writes++;
}
static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
BlockRequest *blkreq;
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_WRITE);
trace_virtio_blk_handle_write(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;
}
if (mrb->num_writes == 32) {
virtio_submit_multiwrite(req->dev->bs, mrb);
}
blkreq = &mrb->blkreq[mrb->num_writes];
blkreq->sector = sector;
blkreq->nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
blkreq->qiov = &req->qiov;
blkreq->cb = virtio_blk_rw_complete;
blkreq->opaque = req;
blkreq->error = 0;
mrb->num_writes++;
}
static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
bdrv_acct_start(req->dev->bs, &req->acct, 0, BDRV_ACCT_FLUSH);
/*
* Make sure all outstanding writes are posted to the backing device.
*/
virtio_submit_multiwrite(req->dev->bs, mrb);
bdrv_aio_flush(req->dev->bs, virtio_blk_flush_complete, req);
}
static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
BlockDriverAIOCB *acb;
/*
* Make sure all outstanding writes are posted to the backing device.
*/
virtio_submit_multiwrite(req->dev->bs, mrb);
acb = bdrv_aio_flush(req->dev->bs, virtio_blk_flush_complete, req);
if (!acb) {
virtio_blk_flush_complete(req, -EIO);
}
}
static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
VirtIOBlockReq *req;
MultiReqBuffer mrb = {
.num_writes = 0,
};
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
/* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
* dataplane here instead of waiting for .set_status().
*/
if (s->dataplane) {
virtio_blk_data_plane_start(s->dataplane);
return;
}
#endif
while ((req = virtio_blk_get_request(s))) {
virtio_blk_handle_request(req, &mrb);
}
virtio_submit_multiwrite(s->bs, &mrb);
/*
* FIXME: Want to check for completions before returning to guest mode,
* so cached reads and writes are reported as quickly as possible. But
* that should be done in the generic block layer.
*/
}
static void virtio_blk_dma_restart_bh(void *opaque)
{
VirtIOBlock *s = opaque;
VirtIOBlockReq *req = s->rq;
MultiReqBuffer mrb = {
.num_writes = 0,
};
qemu_bh_delete(s->bh);
s->bh = NULL;
s->rq = NULL;
while (req) {
virtio_blk_handle_request(req, &mrb);
req = req->next;
}
virtio_submit_multiwrite(s->bs, &mrb);
}
static void virtio_blk_dma_restart_cb(void *opaque, int running,
RunState state)
{
VirtIOBlock *s = opaque;
if (!running) {
return;
}
if (!s->bh) {
s->bh = aio_bh_new(bdrv_get_aio_context(s->blk.conf.bs),
virtio_blk_dma_restart_bh, s);
qemu_bh_schedule(s->bh);
}
}
static void handle_notify(EventNotifier *e)
{
VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
host_notifier);
VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
event_notifier_test_and_clear(&s->host_notifier);
blk_io_plug(s->conf->conf.blk);
for (;;) {
MultiReqBuffer mrb = {
.num_writes = 0,
};
int ret;
/* Disable guest->host notifies to avoid unnecessary vmexits */
vring_disable_notification(s->vdev, &s->vring);
for (;;) {
VirtIOBlockReq *req = virtio_blk_alloc_request(vblk);
ret = vring_pop(s->vdev, &s->vring, &req->elem);
if (ret < 0) {
virtio_blk_free_request(req);
break; /* no more requests */
}
trace_virtio_blk_data_plane_process_request(s, req->elem.out_num,
req->elem.in_num,
req->elem.index);
virtio_blk_handle_request(req, &mrb);
}
virtio_submit_multiwrite(s->conf->conf.blk, &mrb);
if (likely(ret == -EAGAIN)) { /* vring emptied */
/* Re-enable guest->host notifies and stop processing the vring.
* But if the guest has snuck in more descriptors, keep processing.
*/
if (vring_enable_notification(s->vdev, &s->vring)) {
break;
}
} else { /* fatal error */
break;
}
}
blk_io_unplug(s->conf->conf.blk);
}
/* Context: QEMU global mutex held */
void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
VirtIOBlockDataPlane **dataplane,
Error **errp)
{
VirtIOBlockDataPlane *s;
Error *local_err = NULL;
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
*dataplane = NULL;
if (!conf->data_plane && !conf->iothread) {
return;
}
/* Don't try if transport does not support notifiers. */
if (!k->set_guest_notifiers || !k->set_host_notifier) {
error_setg(errp,
"device is incompatible with x-data-plane "
"(transport does not support notifiers)");
return;
}
/* If dataplane is (re-)enabled while the guest is running there could be
* block jobs that can conflict.
*/
if (blk_op_is_blocked(conf->conf.blk, BLOCK_OP_TYPE_DATAPLANE,
&local_err)) {
error_setg(errp, "cannot start dataplane thread: %s",
error_get_pretty(local_err));
error_free(local_err);
return;
}
s = g_new0(VirtIOBlockDataPlane, 1);
s->vdev = vdev;
s->conf = conf;
if (conf->iothread) {
s->iothread = conf->iothread;
object_ref(OBJECT(s->iothread));
} else {
/* Create per-device IOThread if none specified. This is for
* x-data-plane option compatibility. If x-data-plane is removed we
* can drop this.
*/
object_initialize(&s->internal_iothread_obj,
sizeof(s->internal_iothread_obj),
TYPE_IOTHREAD);
user_creatable_complete(OBJECT(&s->internal_iothread_obj), &error_abort);
s->iothread = &s->internal_iothread_obj;
}
s->ctx = iothread_get_aio_context(s->iothread);
s->bh = aio_bh_new(s->ctx, notify_guest_bh, s);
error_setg(&s->blocker, "block device is in use by data plane");
blk_op_block_all(conf->conf.blk, s->blocker);
blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_RESIZE, s->blocker);
blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_DRIVE_DEL, s->blocker);
*dataplane = s;
}
