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);
}
/* 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, NULL);
/* Drain and switch bs back to the QEMU main loop */
bdrv_set_aio_context(s->blk->conf.bs, 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 mirror_start_job(const char *job_id, BlockDriverState *bs,
int creation_flags, BlockDriverState *target,
const char *replaces, int64_t speed,
uint32_t granularity, int64_t buf_size,
BlockMirrorBackingMode backing_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
bool unmap,
BlockCompletionFunc *cb,
void *opaque,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base,
bool auto_complete, const char *filter_node_name,
bool is_mirror,
Error **errp)
{
MirrorBlockJob *s;
BlockDriverState *mirror_top_bs;
bool target_graph_mod;
bool target_is_backing;
Error *local_err = NULL;
int ret;
if (granularity == 0) {
granularity = bdrv_get_default_bitmap_granularity(target);
}
assert(is_power_of_2(granularity));
if (buf_size < 0) {
error_setg(errp, "Invalid parameter 'buf-size'");
return;
}
if (buf_size == 0) {
buf_size = DEFAULT_MIRROR_BUF_SIZE;
}
/* In the case of active commit, add dummy driver to provide consistent
* reads on the top, while disabling it in the intermediate nodes, and make
* the backing chain writable. */
mirror_top_bs = bdrv_new_open_driver(&bdrv_mirror_top, filter_node_name,
BDRV_O_RDWR, errp);
if (mirror_top_bs == NULL) {
return;
}
if (!filter_node_name) {
mirror_top_bs->implicit = true;
}
mirror_top_bs->total_sectors = bs->total_sectors;
mirror_top_bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
mirror_top_bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED;
bdrv_set_aio_context(mirror_top_bs, bdrv_get_aio_context(bs));
/* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
* it alive until block_job_create() succeeds even if bs has no parent. */
bdrv_ref(mirror_top_bs);
bdrv_drained_begin(bs);
bdrv_append(mirror_top_bs, bs, &local_err);
bdrv_drained_end(bs);
if (local_err) {
bdrv_unref(mirror_top_bs);
error_propagate(errp, local_err);
return;
}
/* Make sure that the source is not resized while the job is running */
s = block_job_create(job_id, driver, NULL, mirror_top_bs,
BLK_PERM_CONSISTENT_READ,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed,
creation_flags, cb, opaque, errp);
if (!s) {
goto fail;
}
/* The block job now has a reference to this node */
bdrv_unref(mirror_top_bs);
s->source = bs;
s->mirror_top_bs = mirror_top_bs;
/* No resize for the target either; while the mirror is still running, a
* consistent read isn't necessarily possible. We could possibly allow
* writes and graph modifications, though it would likely defeat the
* purpose of a mirror, so leave them blocked for now.
*
* In the case of active commit, things look a bit different, though,
* because the target is an already populated backing file in active use.
* We can allow anything except resize there.*/
target_is_backing = bdrv_chain_contains(bs, target);
target_graph_mod = (backing_mode != MIRROR_LEAVE_BACKING_CHAIN);
s->target = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE |
(target_graph_mod ? BLK_PERM_GRAPH_MOD : 0),
BLK_PERM_WRITE_UNCHANGED |
(target_is_backing ? BLK_PERM_CONSISTENT_READ |
BLK_PERM_WRITE |
BLK_PERM_GRAPH_MOD : 0));
ret = blk_insert_bs(s->target, target, errp);
if (ret < 0) {
goto fail;
}
if (is_mirror) {
/* XXX: Mirror target could be a NBD server of target QEMU in the case
* of non-shared block migration. To allow migration completion, we
* have to allow "inactivate" of the target BB. When that happens, we
* know the job is drained, and the vcpus are stopped, so no write
* operation will be performed. Block layer already has assertions to
* ensure that. */
blk_set_force_allow_inactivate(s->target);
}
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
s->on_target_error = on_target_error;
s->is_none_mode = is_none_mode;
s->backing_mode = backing_mode;
s->base = base;
s->granularity = granularity;
s->buf_size = ROUND_UP(buf_size, granularity);
s->unmap = unmap;
if (auto_complete) {
s->should_complete = true;
}
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
if (!s->dirty_bitmap) {
goto fail;
}
/* Required permissions are already taken with blk_new() */
block_job_add_bdrv(&s->common, "target", target, 0, BLK_PERM_ALL,
&error_abort);
/* In commit_active_start() all intermediate nodes disappear, so
* any jobs in them must be blocked */
if (target_is_backing) {
BlockDriverState *iter;
for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
/* XXX BLK_PERM_WRITE needs to be allowed so we don't block
* ourselves at s->base (if writes are blocked for a node, they are
* also blocked for its backing file). The other options would be a
* second filter driver above s->base (== target). */
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
errp);
if (ret < 0) {
goto fail;
}
}
}
trace_mirror_start(bs, s, opaque);
block_job_start(&s->common);
return;
fail:
if (s) {
/* Make sure this BDS does not go away until we have completed the graph
* changes below */
bdrv_ref(mirror_top_bs);
g_free(s->replaces);
blk_unref(s->target);
block_job_early_fail(&s->common);
}
bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
&error_abort);
bdrv_replace_node(mirror_top_bs, backing_bs(mirror_top_bs), &error_abort);
bdrv_unref(mirror_top_bs);
}
/* commit COW file into the raw image */
int bdrv_commit(BlockDriverState *bs)
{
BlockBackend *src, *backing;
BlockDriverState *backing_file_bs = NULL;
BlockDriverState *commit_top_bs = NULL;
BlockDriver *drv = bs->drv;
int64_t offset, length, backing_length;
int ro;
int64_t n;
int ret = 0;
uint8_t *buf = NULL;
Error *local_err = NULL;
if (!drv)
return -ENOMEDIUM;
if (!bs->backing) {
return -ENOTSUP;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) ||
bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) {
return -EBUSY;
}
ro = bs->backing->bs->read_only;
if (ro) {
if (bdrv_reopen_set_read_only(bs->backing->bs, false, NULL)) {
return -EACCES;
}
}
src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
ret = blk_insert_bs(src, bs, &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
}
/* Insert commit_top block node above backing, so we can write to it */
backing_file_bs = backing_bs(bs);
commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
&local_err);
if (commit_top_bs == NULL) {
error_report_err(local_err);
goto ro_cleanup;
}
bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(backing_file_bs));
bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
ret = blk_insert_bs(backing, backing_file_bs, &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
}
length = blk_getlength(src);
if (length < 0) {
ret = length;
goto ro_cleanup;
}
backing_length = blk_getlength(backing);
if (backing_length < 0) {
ret = backing_length;
goto ro_cleanup;
}
/* If our top snapshot is larger than the backing file image,
* grow the backing file image if possible. If not possible,
* we must return an error */
if (length > backing_length) {
ret = blk_truncate(backing, length, PREALLOC_MODE_OFF, &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
}
}
/* blk_try_blockalign() for src will choose an alignment that works for
* backing as well, so no need to compare the alignment manually. */
buf = blk_try_blockalign(src, COMMIT_BUF_SIZE);
if (buf == NULL) {
ret = -ENOMEM;
goto ro_cleanup;
}
for (offset = 0; offset < length; offset += n) {
ret = bdrv_is_allocated(bs, offset, COMMIT_BUF_SIZE, &n);
if (ret < 0) {
goto ro_cleanup;
}
if (ret) {
ret = blk_pread(src, offset, buf, n);
if (ret < 0) {
goto ro_cleanup;
}
ret = blk_pwrite(backing, offset, buf, n, 0);
if (ret < 0) {
goto ro_cleanup;
}
}
}
if (drv->bdrv_make_empty) {
ret = drv->bdrv_make_empty(bs);
if (ret < 0) {
goto ro_cleanup;
}
blk_flush(src);
}
/*
* Make sure all data we wrote to the backing device is actually
* stable on disk.
*/
blk_flush(backing);
ret = 0;
ro_cleanup:
qemu_vfree(buf);
blk_unref(backing);
if (backing_file_bs) {
bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
}
bdrv_unref(commit_top_bs);
blk_unref(src);
if (ro) {
/* ignoring error return here */
bdrv_reopen_set_read_only(bs->backing->bs, true, NULL);
}
return ret;
}
void commit_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, BlockDriverState *top,
int creation_flags, int64_t speed,
BlockdevOnError on_error, const char *backing_file_str,
const char *filter_node_name, Error **errp)
{
CommitBlockJob *s;
BlockDriverState *iter;
BlockDriverState *commit_top_bs = NULL;
Error *local_err = NULL;
int ret;
assert(top != bs);
if (top == base) {
error_setg(errp, "Invalid files for merge: top and base are the same");
return;
}
s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL,
speed, creation_flags, NULL, NULL, errp);
if (!s) {
return;
}
/* convert base to r/w, if necessary */
s->base_read_only = bdrv_is_read_only(base);
if (s->base_read_only) {
if (bdrv_reopen_set_read_only(base, false, errp) != 0) {
goto fail;
}
}
/* Insert commit_top block node above top, so we can block consistent read
* on the backing chain below it */
commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
errp);
if (commit_top_bs == NULL) {
goto fail;
}
if (!filter_node_name) {
commit_top_bs->implicit = true;
}
commit_top_bs->total_sectors = top->total_sectors;
bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(top));
bdrv_set_backing_hd(commit_top_bs, top, &local_err);
if (local_err) {
bdrv_unref(commit_top_bs);
commit_top_bs = NULL;
error_propagate(errp, local_err);
goto fail;
}
bdrv_replace_node(top, commit_top_bs, &local_err);
if (local_err) {
bdrv_unref(commit_top_bs);
commit_top_bs = NULL;
error_propagate(errp, local_err);
goto fail;
}
s->commit_top_bs = commit_top_bs;
bdrv_unref(commit_top_bs);
/* Block all nodes between top and base, because they will
* disappear from the chain after this operation. */
assert(bdrv_chain_contains(top, base));
for (iter = top; iter != base; iter = backing_bs(iter)) {
/* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
* at s->base (if writes are blocked for a node, they are also blocked
* for its backing file). The other options would be a second filter
* driver above s->base. */
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
errp);
if (ret < 0) {
goto fail;
}
}
if (bdrv_freeze_backing_chain(commit_top_bs, base, errp) < 0) {
goto fail;
}
s->chain_frozen = true;
ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
if (ret < 0) {
goto fail;
}
s->base = blk_new(BLK_PERM_CONSISTENT_READ
| BLK_PERM_WRITE
| BLK_PERM_RESIZE,
BLK_PERM_CONSISTENT_READ
| BLK_PERM_GRAPH_MOD
| BLK_PERM_WRITE_UNCHANGED);
ret = blk_insert_bs(s->base, base, errp);
if (ret < 0) {
goto fail;
}
s->base_bs = base;
/* Required permissions are already taken with block_job_add_bdrv() */
s->top = blk_new(0, BLK_PERM_ALL);
ret = blk_insert_bs(s->top, top, errp);
if (ret < 0) {
goto fail;
}
s->backing_file_str = g_strdup(backing_file_str);
s->on_error = on_error;
trace_commit_start(bs, base, top, s);
job_start(&s->common.job);
return;
fail:
if (s->chain_frozen) {
bdrv_unfreeze_backing_chain(commit_top_bs, base);
}
if (s->base) {
blk_unref(s->base);
}
if (s->top) {
blk_unref(s->top);
}
job_early_fail(&s->common.job);
/* commit_top_bs has to be replaced after deleting the block job,
* otherwise this would fail because of lack of permissions. */
if (commit_top_bs) {
bdrv_replace_node(commit_top_bs, top, &error_abort);
}
}
/* 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);
VirtQueue *vq;
int r;
if (s->started || s->disabled) {
return;
}
if (s->starting) {
return;
}
s->starting = true;
vq = virtio_get_queue(s->vdev, 0);
if (!vring_setup(&s->vring, s->vdev, 0)) {
goto fail_vring;
}
/* 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(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->host_notifier = *virtio_queue_get_host_notifier(vq);
s->saved_complete_request = vblk->complete_request;
vblk->complete_request = complete_request_vring;
s->starting = false;
s->started = true;
trace_virtio_blk_data_plane_start(s);
bdrv_set_aio_context(s->blk->conf.bs, s->ctx);
/* Kick right away to begin processing requests already in vring */
event_notifier_set(virtio_queue_get_host_notifier(vq));
/* Get this show started by hooking up our callbacks */
aio_context_acquire(s->ctx);
aio_set_event_notifier(s->ctx, &s->host_notifier, handle_notify);
aio_context_release(s->ctx);
return;
fail_host_notifier:
k->set_guest_notifiers(qbus->parent, 1, false);
fail_guest_notifiers:
vring_teardown(&s->vring, s->vdev, 0);
s->disabled = true;
fail_vring:
s->starting = false;
}
