static void mirror_complete(BlockJob *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
Error *local_err = NULL;
int ret;
ret = bdrv_open_backing_file(s->target, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return;
}
if (!s->synced) {
error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
return;
}
/* check the target bs is not blocked and block all operations on it */
if (s->replaces) {
s->to_replace = check_to_replace_node(s->replaces, &local_err);
if (!s->to_replace) {
error_propagate(errp, local_err);
return;
}
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);
}
s->should_complete = true;
block_job_resume(job);
}
void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
int64_t speed,
BlockdevOnError on_error,
BlockCompletionFunc *cb,
void *opaque, Error **errp)
{
int64_t length, base_length;
int orig_base_flags;
int ret;
Error *local_err = NULL;
orig_base_flags = bdrv_get_flags(base);
if (bdrv_reopen(base, bs->open_flags, errp)) {
return;
}
length = bdrv_getlength(bs);
if (length < 0) {
error_setg_errno(errp, -length,
"Unable to determine length of %s", bs->filename);
goto error_restore_flags;
}
base_length = bdrv_getlength(base);
if (base_length < 0) {
error_setg_errno(errp, -base_length,
"Unable to determine length of %s", base->filename);
goto error_restore_flags;
}
if (length > base_length) {
ret = bdrv_truncate(base, length);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Top image %s is larger than base image %s, and "
"resize of base image failed",
bs->filename, base->filename);
goto error_restore_flags;
}
}
bdrv_ref(base);
mirror_start_job(bs, base, NULL, speed, 0, 0,
on_error, on_error, cb, opaque, &local_err,
&commit_active_job_driver, false, base);
if (local_err) {
error_propagate(errp, local_err);
goto error_restore_flags;
}
return;
error_restore_flags:
/* ignore error and errp for bdrv_reopen, because we want to propagate
* the original error */
bdrv_reopen(base, orig_base_flags, NULL);
return;
}
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);
}
static void commit_abort(Job *job)
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
BlockDriverState *top_bs = blk_bs(s->top);
if (s->chain_frozen) {
bdrv_unfreeze_backing_chain(s->commit_top_bs, s->base_bs);
}
/* Make sure commit_top_bs and top stay around until bdrv_replace_node() */
bdrv_ref(top_bs);
bdrv_ref(s->commit_top_bs);
if (s->base) {
blk_unref(s->base);
}
/* free the blockers on the intermediate nodes so that bdrv_replace_nodes
* can succeed */
block_job_remove_all_bdrv(&s->common);
/* If bdrv_drop_intermediate() failed (or was not invoked), remove the
* commit filter driver from the backing chain now. Do this as the final
* step so that the 'consistent read' permission can be granted.
*
* XXX Can (or should) we somehow keep 'consistent read' blocked even
* after the failed/cancelled commit job is gone? If we already wrote
* something to base, the intermediate images aren't valid any more. */
bdrv_child_try_set_perm(s->commit_top_bs->backing, 0, BLK_PERM_ALL,
&error_abort);
bdrv_replace_node(s->commit_top_bs, backing_bs(s->commit_top_bs),
&error_abort);
bdrv_unref(s->commit_top_bs);
bdrv_unref(top_bs);
}
static void mirror_exit(BlockJob *job, void *opaque)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
BlockDriverState *src = s->common.bs;
/* Make sure that the source BDS doesn't go away before we called
* block_job_completed(). */
bdrv_ref(src);
if (s->to_replace) {
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
}
if (s->should_complete && data->ret == 0) {
BlockDriverState *to_replace = s->common.bs;
if (s->to_replace) {
to_replace = s->to_replace;
}
if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
}
bdrv_replace_in_backing_chain(to_replace, s->target);
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
if (replace_aio_context) {
aio_context_release(replace_aio_context);
}
g_free(s->replaces);
bdrv_op_unblock_all(s->target, s->common.blocker);
bdrv_unref(s->target);
block_job_completed(&s->common, data->ret);
g_free(data);
bdrv_unref(src);
}
void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
int64_t speed, BlockCompletionFunc *cb,
void *opaque, Error **errp)
{
BlockJob *job;
if (bs->job) {
error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
return NULL;
}
bdrv_ref(bs);
job = g_malloc0(driver->instance_size);
error_setg(&job->blocker, "block device is in use by block job: %s",
BlockJobType_lookup[driver->job_type]);
bdrv_op_block_all(bs, job->blocker);
bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
job->driver = driver;
job->bs = bs;
job->cb = cb;
job->opaque = opaque;
job->busy = true;
bs->job = job;
/* Only set speed when necessary to avoid NotSupported error */
if (speed != 0) {
Error *local_err = NULL;
block_job_set_speed(job, speed, &local_err);
if (local_err) {
bs->job = NULL;
bdrv_op_unblock_all(bs, job->blocker);
error_free(job->blocker);
g_free(job);
error_propagate(errp, local_err);
return NULL;
}
}
return job;
}
void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
int64_t speed, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
BlockJob *job;
if (bs->job || bdrv_in_use(bs)) {
error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
return NULL;
}
bdrv_ref(bs);
bdrv_set_in_use(bs, 1);
job = g_malloc0(driver->instance_size);
job->driver = driver;
job->bs = bs;
job->cb = cb;
job->opaque = opaque;
job->busy = true;
bs->job = job;
/* Only set speed when necessary to avoid NotSupported error */
if (speed != 0) {
Error *local_err = NULL;
block_job_set_speed(job, speed, &local_err);
if (error_is_set(&local_err)) {
bs->job = NULL;
g_free(job);
bdrv_set_in_use(bs, 0);
error_propagate(errp, local_err);
return NULL;
}
}
return job;
}
static void mirror_exit(BlockJob *job, void *opaque)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
BlockDriverState *src = s->source;
BlockDriverState *target_bs = blk_bs(s->target);
BlockDriverState *mirror_top_bs = s->mirror_top_bs;
Error *local_err = NULL;
bdrv_release_dirty_bitmap(src, s->dirty_bitmap);
/* Make sure that the source BDS doesn't go away before we called
* block_job_completed(). */
bdrv_ref(src);
bdrv_ref(mirror_top_bs);
bdrv_ref(target_bs);
/* Remove target parent that still uses BLK_PERM_WRITE/RESIZE before
* inserting target_bs at s->to_replace, where we might not be able to get
* these permissions.
*
* Note that blk_unref() alone doesn't necessarily drop permissions because
* we might be running nested inside mirror_drain(), which takes an extra
* reference, so use an explicit blk_set_perm() first. */
blk_set_perm(s->target, 0, BLK_PERM_ALL, &error_abort);
blk_unref(s->target);
s->target = NULL;
/* We don't access the source any more. Dropping any WRITE/RESIZE is
* required before it could become a backing file of target_bs. */
bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
&error_abort);
if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
BlockDriverState *backing = s->is_none_mode ? src : s->base;
if (backing_bs(target_bs) != backing) {
bdrv_set_backing_hd(target_bs, backing, &local_err);
if (local_err) {
error_report_err(local_err);
data->ret = -EPERM;
}
}
}
if (s->to_replace) {
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
}
if (s->should_complete && data->ret == 0) {
BlockDriverState *to_replace = src;
if (s->to_replace) {
to_replace = s->to_replace;
}
if (bdrv_get_flags(target_bs) != bdrv_get_flags(to_replace)) {
bdrv_reopen(target_bs, bdrv_get_flags(to_replace), NULL);
}
/* The mirror job has no requests in flight any more, but we need to
* drain potential other users of the BDS before changing the graph. */
bdrv_drained_begin(target_bs);
bdrv_replace_node(to_replace, target_bs, &local_err);
bdrv_drained_end(target_bs);
if (local_err) {
error_report_err(local_err);
data->ret = -EPERM;
}
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
if (replace_aio_context) {
aio_context_release(replace_aio_context);
}
g_free(s->replaces);
bdrv_unref(target_bs);
/* Remove the mirror filter driver from the graph. Before this, get rid of
* the blockers on the intermediate nodes so that the resulting state is
* valid. Also give up permissions on mirror_top_bs->backing, which might
* block the removal. */
block_job_remove_all_bdrv(job);
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);
/* We just changed the BDS the job BB refers to (with either or both of the
* bdrv_replace_node() calls), so switch the BB back so the cleanup does
* the right thing. We don't need any permissions any more now. */
blk_remove_bs(job->blk);
blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
blk_insert_bs(job->blk, mirror_top_bs, &error_abort);
block_job_completed(&s->common, data->ret);
g_free(data);
bdrv_drained_end(src);
bdrv_unref(mirror_top_bs);
bdrv_unref(src);
}
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);
}
