/* Context: QEMU global mutex held */
void virtio_scsi_dataplane_start(VirtIOSCSI *s)
{
int i;
int rc;
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
if (s->dataplane_started ||
s->dataplane_starting ||
s->dataplane_fenced ||
s->ctx != iothread_get_aio_context(vs->conf.iothread)) {
return;
}
s->dataplane_starting = true;
/* Set up guest notifier (irq) */
rc = k->set_guest_notifiers(qbus->parent, vs->conf.num_queues + 2, true);
if (rc != 0) {
fprintf(stderr, "virtio-scsi: Failed to set guest notifiers (%d), "
"ensure -enable-kvm is set\n", rc);
goto fail_guest_notifiers;
}
aio_context_acquire(s->ctx);
rc = virtio_scsi_vring_init(s, vs->ctrl_vq, 0);
if (rc) {
goto fail_vrings;
}
rc = virtio_scsi_vring_init(s, vs->event_vq, 1);
if (rc) {
goto fail_vrings;
}
for (i = 0; i < vs->conf.num_queues; i++) {
rc = virtio_scsi_vring_init(s, vs->cmd_vqs[i], i + 2);
if (rc) {
goto fail_vrings;
}
}
s->dataplane_starting = false;
s->dataplane_started = true;
aio_context_release(s->ctx);
return;
fail_vrings:
virtio_scsi_clear_aio(s);
aio_context_release(s->ctx);
for (i = 0; i < vs->conf.num_queues + 2; i++) {
k->set_host_notifier(qbus->parent, i, false);
}
k->set_guest_notifiers(qbus->parent, vs->conf.num_queues + 2, false);
fail_guest_notifiers:
s->dataplane_fenced = true;
s->dataplane_starting = false;
s->dataplane_started = true;
}
BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
bool query_nodes,
Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
/* Just to be safe if query_nodes is not always initialized */
query_nodes = has_query_nodes && query_nodes;
while (next_query_bds(&blk, &bs, query_nodes)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk ? blk_get_aio_context(blk)
: bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_stats(blk, bs, !query_nodes);
aio_context_release(ctx);
*p_next = info;
p_next = &info->next;
}
return head;
}
static void scsi_write_complete(void * opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
SCSIDevice *s = r->req.dev;
DPRINTF("scsi_write_complete() ret = %d\n", ret);
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
aio_context_acquire(blk_get_aio_context(s->conf.blk));
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
goto done;
}
if (r->req.cmd.buf[0] == MODE_SELECT && r->req.cmd.buf[4] == 12 &&
s->type == TYPE_TAPE) {
s->blocksize = (r->buf[9] << 16) | (r->buf[10] << 8) | r->buf[11];
DPRINTF("block size %d\n", s->blocksize);
}
scsi_command_complete_noio(r, ret);
done:
aio_context_release(blk_get_aio_context(s->conf.blk));
}
static void test_acquire(void)
{
QemuThread thread;
AcquireTestData data;
/* Dummy event notifier ensures aio_poll() will block */
event_notifier_init(&data.notifier, false);
set_event_notifier(ctx, &data.notifier, dummy_notifier_read);
g_assert(!aio_poll(ctx, false)); /* consume aio_notify() */
qemu_mutex_init(&data.start_lock);
qemu_mutex_lock(&data.start_lock);
data.thread_acquired = false;
qemu_thread_create(&thread, "test_acquire_thread",
test_acquire_thread,
&data, QEMU_THREAD_JOINABLE);
/* Block in aio_poll(), let other thread kick us and acquire context */
aio_context_acquire(ctx);
qemu_mutex_unlock(&data.start_lock); /* let the thread run */
g_assert(aio_poll(ctx, true));
g_assert(!data.thread_acquired);
aio_context_release(ctx);
qemu_thread_join(&thread);
set_event_notifier(ctx, &data.notifier, NULL);
event_notifier_cleanup(&data.notifier);
g_assert(data.thread_acquired);
}
int bdrv_all_create_snapshot(QEMUSnapshotInfo *sn,
BlockDriverState *vm_state_bs,
uint64_t vm_state_size,
BlockDriverState **first_bad_bs)
{
int err = 0;
BlockDriverState *bs = NULL;
while (err == 0 && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (bs == vm_state_bs) {
sn->vm_state_size = vm_state_size;
err = bdrv_snapshot_create(bs, sn);
} else if (bdrv_can_snapshot(bs)) {
sn->vm_state_size = 0;
err = bdrv_snapshot_create(bs, sn);
}
aio_context_release(ctx);
}
*first_bad_bs = bs;
return err;
}
static void *iothread_run(void *opaque)
{
IOThread *iothread = opaque;
bool blocking;
rcu_register_thread();
qemu_mutex_lock(&iothread->init_done_lock);
iothread->thread_id = qemu_get_thread_id();
qemu_cond_signal(&iothread->init_done_cond);
qemu_mutex_unlock(&iothread->init_done_lock);
while (!iothread->stopping) {
aio_context_acquire(iothread->ctx);
blocking = true;
while (!iothread->stopping && aio_poll(iothread->ctx, blocking)) {
/* Progress was made, keep going */
blocking = false;
}
aio_context_release(iothread->ctx);
}
rcu_unregister_thread();
return NULL;
}
static void blk_bh(void *opaque)
{
struct XenBlkDev *blkdev = opaque;
aio_context_acquire(blkdev->ctx);
blk_handle_requests(blkdev);
aio_context_release(blkdev->ctx);
}
static void xen_block_dataplane_bh(void *opaque)
{
XenBlockDataPlane *dataplane = opaque;
aio_context_acquire(dataplane->ctx);
xen_block_handle_requests(dataplane);
aio_context_release(dataplane->ctx);
}
BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
bool query_nodes,
Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockBackend *blk;
BlockDriverState *bs;
/* Just to be safe if query_nodes is not always initialized */
if (has_query_nodes && query_nodes) {
for (bs = bdrv_next_node(NULL); bs; bs = bdrv_next_node(bs)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_bds_stats(bs, false);
aio_context_release(ctx);
*p_next = info;
p_next = &info->next;
}
} else {
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk_get_aio_context(blk);
BlockStats *s;
aio_context_acquire(ctx);
s = bdrv_query_bds_stats(blk_bs(blk), true);
s->has_device = true;
s->device = g_strdup(blk_name(blk));
bdrv_query_blk_stats(s->stats, blk);
aio_context_release(ctx);
info->value = s;
*p_next = info;
p_next = &info->next;
}
}
return head;
}
static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
struct virtio_blk_config blkcfg;
memcpy(&blkcfg, config, sizeof(blkcfg));
aio_context_acquire(bdrv_get_aio_context(s->bs));
bdrv_set_enable_write_cache(s->bs, blkcfg.wce != 0);
aio_context_release(bdrv_get_aio_context(s->bs));
}
static void scsi_command_complete(void *opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
SCSIDevice *s = r->req.dev;
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
aio_context_acquire(blk_get_aio_context(s->conf.blk));
scsi_command_complete_noio(r, ret);
aio_context_release(blk_get_aio_context(s->conf.blk));
}
/* Context: QEMU global mutex held */
void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
{
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
int r;
if (vblk->dataplane_started || s->starting) {
return;
}
s->starting = true;
s->vq = virtio_get_queue(s->vdev, 0);
/* Set up guest notifier (irq) */
r = k->set_guest_notifiers(qbus->parent, 1, true);
if (r != 0) {
fprintf(stderr, "virtio-blk failed to set guest notifier (%d), "
"ensure -enable-kvm is set\n", r);
goto fail_guest_notifiers;
}
s->guest_notifier = virtio_queue_get_guest_notifier(s->vq);
/* Set up virtqueue notify */
r = k->set_host_notifier(qbus->parent, 0, true);
if (r != 0) {
fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
goto fail_host_notifier;
}
s->starting = false;
vblk->dataplane_started = true;
trace_virtio_blk_data_plane_start(s);
blk_set_aio_context(s->conf->conf.blk, s->ctx);
/* Kick right away to begin processing requests already in vring */
event_notifier_set(virtio_queue_get_host_notifier(s->vq));
/* Get this show started by hooking up our callbacks */
aio_context_acquire(s->ctx);
virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx,
virtio_blk_data_plane_handle_output);
aio_context_release(s->ctx);
return;
fail_host_notifier:
k->set_guest_notifiers(qbus->parent, 1, false);
fail_guest_notifiers:
vblk->dataplane_disabled = true;
s->starting = false;
vblk->dataplane_started = true;
}
static void block_job_defer_to_main_loop_bh(void *opaque)
{
BlockJobDeferToMainLoopData *data = opaque;
AioContext *aio_context;
qemu_bh_delete(data->bh);
/* Prevent race with block_job_defer_to_main_loop() */
aio_context_acquire(data->aio_context);
/* Fetch BDS AioContext again, in case it has changed */
aio_context = bdrv_get_aio_context(data->job->bs);
aio_context_acquire(aio_context);
data->fn(data->job, data->opaque);
aio_context_release(aio_context);
aio_context_release(data->aio_context);
g_free(data);
}
void qmp_job_complete(const char *id, Error **errp)
{
AioContext *aio_context;
Job *job = find_job(id, &aio_context, errp);
if (!job) {
return;
}
trace_qmp_job_complete(job);
job_complete(job, errp);
aio_context_release(aio_context);
}
static void mirror_complete(BlockJob *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
BlockDriverState *target;
target = blk_bs(s->target);
if (!s->synced) {
error_setg(errp, "The active block job '%s' cannot be completed",
job->id);
return;
}
if (s->backing_mode == MIRROR_OPEN_BACKING_CHAIN) {
int ret;
assert(!target->backing);
ret = bdrv_open_backing_file(target, NULL, "backing", errp);
if (ret < 0) {
return;
}
}
/* block all operations on to_replace bs */
if (s->replaces) {
AioContext *replace_aio_context;
s->to_replace = bdrv_find_node(s->replaces);
if (!s->to_replace) {
error_setg(errp, "Node name '%s' not found", s->replaces);
return;
}
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
/* TODO Translate this into permission system. Current definition of
* GRAPH_MOD would require to request it for the parents; they might
* not even be BlockDriverStates, however, so a BdrvChild can't address
* them. May need redefinition of GRAPH_MOD. */
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
bdrv_ref(s->to_replace);
aio_context_release(replace_aio_context);
}
s->should_complete = true;
block_job_enter(&s->common);
}
BlockDriverState *bdrv_all_find_vmstate_bs(void)
{
bool not_found = true;
BlockDriverState *bs = NULL;
while (not_found && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
not_found = !bdrv_can_snapshot(bs);
aio_context_release(ctx);
}
return bs;
}
static JobInfo *job_query_single(Job *job, Error **errp)
{
JobInfo *info;
assert(!job_is_internal(job));
info = g_new(JobInfo, 1);
*info = (JobInfo) {
.id = g_strdup(job->id),
.type = job_type(job),
.status = job->status,
.current_progress = job->progress_current,
.total_progress = job->progress_total,
.has_error = !!job->err,
.error = job->err ? \
g_strdup(error_get_pretty(job->err)) : NULL,
};
return info;
}
JobInfoList *qmp_query_jobs(Error **errp)
{
JobInfoList *head = NULL, **p_next = &head;
Job *job;
for (job = job_next(NULL); job; job = job_next(job)) {
JobInfoList *elem;
AioContext *aio_context;
if (job_is_internal(job)) {
continue;
}
elem = g_new0(JobInfoList, 1);
aio_context = job->aio_context;
aio_context_acquire(aio_context);
elem->value = job_query_single(job, errp);
aio_context_release(aio_context);
if (!elem->value) {
g_free(elem);
qapi_free_JobInfoList(head);
return NULL;
}
*p_next = elem;
p_next = &elem->next;
}
return head;
}
static void release_drive(Object *obj, const char *name, void *opaque)
{
DeviceState *dev = DEVICE(obj);
Property *prop = opaque;
BlockBackend **ptr = qdev_get_prop_ptr(dev, prop);
if (*ptr) {
AioContext *ctx = blk_get_aio_context(*ptr);
aio_context_acquire(ctx);
blockdev_auto_del(*ptr);
blk_detach_dev(*ptr, dev);
aio_context_release(ctx);
}
}
static void *test_acquire_thread(void *opaque)
{
AcquireTestData *data = opaque;
/* Wait for other thread to let us start */
qemu_mutex_lock(&data->start_lock);
qemu_mutex_unlock(&data->start_lock);
aio_context_acquire(ctx);
aio_context_release(ctx);
data->thread_acquired = true; /* success, we got here */
return NULL;
}
/* Context: QEMU global mutex held */
void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
{
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
unsigned i;
unsigned nvqs = s->conf->num_queues;
if (!vblk->dataplane_started || s->stopping) {
return;
}
/* Better luck next time. */
if (vblk->dataplane_disabled) {
vblk->dataplane_disabled = false;
vblk->dataplane_started = false;
return;
}
s->stopping = true;
trace_virtio_blk_data_plane_stop(s);
aio_context_acquire(s->ctx);
/* Stop notifications for new requests from guest */
for (i = 0; i < nvqs; i++) {
VirtQueue *vq = virtio_get_queue(s->vdev, i);
virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, NULL);
}
/* Drain and switch bs back to the QEMU main loop */
blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());
aio_context_release(s->ctx);
for (i = 0; i < nvqs; i++) {
virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
}
/* Clean up guest notifier (irq) */
k->set_guest_notifiers(qbus->parent, nvqs, false);
vblk->dataplane_started = false;
s->stopping = false;
}
int bdrv_all_goto_snapshot(const char *name, BlockDriverState **first_bad_bs)
{
int err = 0;
BlockDriverState *bs = NULL;
while (err == 0 && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (bdrv_can_snapshot(bs)) {
err = bdrv_snapshot_goto(bs, name);
}
aio_context_release(ctx);
}
*first_bad_bs = bs;
return err;
}
bool bdrv_all_can_snapshot(BlockDriverState **first_bad_bs)
{
bool ok = true;
BlockDriverState *bs = NULL;
while (ok && (bs = bdrv_next(bs))) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (bdrv_is_inserted(bs) && !bdrv_is_read_only(bs)) {
ok = bdrv_can_snapshot(bs);
}
aio_context_release(ctx);
}
*first_bad_bs = bs;
return ok;
}
static void mirror_write_complete(void *opaque, int ret)
{
MirrorOp *op = opaque;
MirrorBlockJob *s = op->s;
aio_context_acquire(blk_get_aio_context(s->common.blk));
if (ret < 0) {
BlockErrorAction action;
bdrv_set_dirty_bitmap(s->dirty_bitmap, op->offset, op->bytes);
action = mirror_error_action(s, false, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
s->ret = ret;
}
}
mirror_iteration_done(op, ret);
aio_context_release(blk_get_aio_context(s->common.blk));
}
void iothread_stop_all(void)
{
Object *container = object_get_objects_root();
BlockDriverState *bs;
BdrvNextIterator it;
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
AioContext *ctx = bdrv_get_aio_context(bs);
if (ctx == qemu_get_aio_context()) {
continue;
}
aio_context_acquire(ctx);
bdrv_set_aio_context(bs, qemu_get_aio_context());
aio_context_release(ctx);
}
object_child_foreach(container, iothread_stop, NULL);
}
static void virtio_blk_ioctl_complete(void *opaque, int status)
{
VirtIOBlockIoctlReq *ioctl_req = opaque;
VirtIOBlockReq *req = ioctl_req->req;
VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
struct virtio_scsi_inhdr *scsi;
struct sg_io_hdr *hdr;
scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
if (status) {
status = VIRTIO_BLK_S_UNSUPP;
virtio_stl_p(vdev, &scsi->errors, 255);
goto out;
}
hdr = &ioctl_req->hdr;
/*
* From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi)
* clear the masked_status field [hence status gets cleared too, see
* block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED
* status has occurred. However they do set DRIVER_SENSE in driver_status
* field. Also a (sb_len_wr > 0) indicates there is a sense buffer.
*/
if (hdr->status == 0 && hdr->sb_len_wr > 0) {
hdr->status = CHECK_CONDITION;
}
virtio_stl_p(vdev, &scsi->errors,
hdr->status | (hdr->msg_status << 8) |
(hdr->host_status << 16) | (hdr->driver_status << 24));
virtio_stl_p(vdev, &scsi->residual, hdr->resid);
virtio_stl_p(vdev, &scsi->sense_len, hdr->sb_len_wr);
virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len);
out:
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
virtio_blk_req_complete(req, status);
virtio_blk_free_request(req);
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
g_free(ioctl_req);
}
BlockStatsList *qmp_query_blockstats(Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockDriverState *bs = NULL;
while ((bs = bdrv_next(bs))) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_stats(bs);
aio_context_release(ctx);
*p_next = info;
p_next = &info->next;
}
return head;
}
static void virtio_blk_flush_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, 0)) {
goto out;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
virtio_blk_free_request(req);
out:
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
/* Context: QEMU global mutex held */
void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
{
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
/* Better luck next time. */
if (s->disabled) {
s->disabled = false;
return;
}
if (!s->started || s->stopping) {
return;
}
s->stopping = true;
vblk->complete_request = s->saved_complete_request;
trace_virtio_blk_data_plane_stop(s);
aio_context_acquire(s->ctx);
/* Stop notifications for new requests from guest */
aio_set_event_notifier(s->ctx, &s->host_notifier, true, NULL);
/* Drain and switch bs back to the QEMU main loop */
blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());
aio_context_release(s->ctx);
/* Sync vring state back to virtqueue so that non-dataplane request
* processing can continue when we disable the host notifier below.
*/
vring_teardown(&s->vring, s->vdev, 0);
k->set_host_notifier(qbus->parent, 0, false);
/* Clean up guest notifier (irq) */
k->set_guest_notifiers(qbus->parent, 1, false);
s->started = false;
s->stopping = false;
}
static void *test_acquire_thread(void *opaque)
{
AcquireTestData *data = opaque;
/* Wait for other thread to let us start */
qemu_mutex_lock(&data->start_lock);
qemu_mutex_unlock(&data->start_lock);
/* event_notifier_set might be called either before or after
* the main thread's call to poll(). The test case's outcome
* should be the same in either case.
*/
event_notifier_set(&data->notifier);
aio_context_acquire(ctx);
aio_context_release(ctx);
data->thread_acquired = true; /* success, we got here */
return NULL;
}
void qmp_block_set_write_threshold(const char *node_name,
uint64_t threshold_bytes,
Error **errp)
{
BlockDriverState *bs;
AioContext *aio_context;
bs = bdrv_find_node(node_name);
if (!bs) {
error_setg(errp, "Device '%s' not found", node_name);
return;
}
aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
bdrv_write_threshold_set(bs, threshold_bytes);
aio_context_release(aio_context);
}