/* @p_info will be set only on success. */
static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
Error **errp)
{
BlockInfo *info = g_malloc0(sizeof(*info));
BlockDriverState *bs = blk_bs(blk);
char *qdev;
/* Skip automatically inserted nodes that the user isn't aware of */
while (bs && bs->drv && bs->implicit) {
bs = backing_bs(bs);
}
info->device = g_strdup(blk_name(blk));
info->type = g_strdup("unknown");
info->locked = blk_dev_is_medium_locked(blk);
info->removable = blk_dev_has_removable_media(blk);
qdev = blk_get_attached_dev_id(blk);
if (qdev && *qdev) {
info->has_qdev = true;
info->qdev = qdev;
} else {
g_free(qdev);
}
if (blk_dev_has_tray(blk)) {
info->has_tray_open = true;
info->tray_open = blk_dev_is_tray_open(blk);
}
if (blk_iostatus_is_enabled(blk)) {
info->has_io_status = true;
info->io_status = blk_iostatus(blk);
}
if (bs && !QLIST_EMPTY(&bs->dirty_bitmaps)) {
info->has_dirty_bitmaps = true;
info->dirty_bitmaps = bdrv_query_dirty_bitmaps(bs);
}
if (bs && bs->drv) {
info->has_inserted = true;
info->inserted = bdrv_block_device_info(blk, bs, errp);
if (info->inserted == NULL) {
goto err;
}
}
*p_info = info;
return;
err:
qapi_free_BlockInfo(info);
}
static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
bool blk_level)
{
BlockStats *s = NULL;
s = g_malloc0(sizeof(*s));
s->stats = g_malloc0(sizeof(*s->stats));
if (!bs) {
return s;
}
/* Skip automatically inserted nodes that the user isn't aware of in
* a BlockBackend-level command. Stay at the exact node for a node-level
* command. */
while (blk_level && bs->drv && bs->implicit) {
bs = backing_bs(bs);
assert(bs);
}
if (bdrv_get_node_name(bs)[0]) {
s->has_node_name = true;
s->node_name = g_strdup(bdrv_get_node_name(bs));
}
s->stats->wr_highest_offset = stat64_get(&bs->wr_highest_offset);
if (bs->file) {
s->has_parent = true;
s->parent = bdrv_query_bds_stats(bs->file->bs, blk_level);
}
if (blk_level && bs->backing) {
s->has_backing = true;
s->backing = bdrv_query_bds_stats(bs->backing->bs, blk_level);
}
return s;
}
void mirror_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *target, const char *replaces,
int64_t speed, uint32_t granularity, int64_t buf_size,
MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
bool unmap, const char *filter_node_name, Error **errp)
{
bool is_none_mode;
BlockDriverState *base;
if (mode == MIRROR_SYNC_MODE_INCREMENTAL) {
error_setg(errp, "Sync mode 'incremental' not supported");
return;
}
is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
base = mode == MIRROR_SYNC_MODE_TOP ? backing_bs(bs) : NULL;
mirror_start_job(job_id, bs, BLOCK_JOB_DEFAULT, target, replaces,
speed, granularity, buf_size, backing_mode,
on_source_error, on_target_error, unmap, NULL, NULL,
&mirror_job_driver, is_none_mode, base, false,
filter_node_name, true, errp);
}
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->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);
}
BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
BlockDriverState *bs, Error **errp)
{
ImageInfo **p_image_info;
BlockDriverState *bs0;
BlockDeviceInfo *info = g_malloc0(sizeof(*info));
info->file = g_strdup(bs->filename);
info->ro = bs->read_only;
info->drv = g_strdup(bs->drv->format_name);
info->encrypted = bs->encrypted;
info->encryption_key_missing = false;
info->cache = g_new(BlockdevCacheInfo, 1);
*info->cache = (BlockdevCacheInfo) {
.writeback = blk ? blk_enable_write_cache(blk) : true,
.direct = !!(bs->open_flags & BDRV_O_NOCACHE),
.no_flush = !!(bs->open_flags & BDRV_O_NO_FLUSH),
};
if (bs->node_name[0]) {
info->has_node_name = true;
info->node_name = g_strdup(bs->node_name);
}
if (bs->backing_file[0]) {
info->has_backing_file = true;
info->backing_file = g_strdup(bs->backing_file);
}
info->detect_zeroes = bs->detect_zeroes;
if (blk && blk_get_public(blk)->throttle_state) {
ThrottleConfig cfg;
throttle_group_get_config(blk, &cfg);
info->bps = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
info->bps_rd = cfg.buckets[THROTTLE_BPS_READ].avg;
info->bps_wr = cfg.buckets[THROTTLE_BPS_WRITE].avg;
info->iops = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
info->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
info->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
info->has_bps_max = cfg.buckets[THROTTLE_BPS_TOTAL].max;
info->bps_max = cfg.buckets[THROTTLE_BPS_TOTAL].max;
info->has_bps_rd_max = cfg.buckets[THROTTLE_BPS_READ].max;
info->bps_rd_max = cfg.buckets[THROTTLE_BPS_READ].max;
info->has_bps_wr_max = cfg.buckets[THROTTLE_BPS_WRITE].max;
info->bps_wr_max = cfg.buckets[THROTTLE_BPS_WRITE].max;
info->has_iops_max = cfg.buckets[THROTTLE_OPS_TOTAL].max;
info->iops_max = cfg.buckets[THROTTLE_OPS_TOTAL].max;
info->has_iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
info->iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
info->iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
info->has_bps_max_length = info->has_bps_max;
info->bps_max_length =
cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
info->has_bps_rd_max_length = info->has_bps_rd_max;
info->bps_rd_max_length =
cfg.buckets[THROTTLE_BPS_READ].burst_length;
info->has_bps_wr_max_length = info->has_bps_wr_max;
info->bps_wr_max_length =
cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
info->has_iops_max_length = info->has_iops_max;
info->iops_max_length =
cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
info->has_iops_rd_max_length = info->has_iops_rd_max;
info->iops_rd_max_length =
cfg.buckets[THROTTLE_OPS_READ].burst_length;
info->has_iops_wr_max_length = info->has_iops_wr_max;
info->iops_wr_max_length =
cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
info->has_iops_size = cfg.op_size;
info->iops_size = cfg.op_size;
info->has_group = true;
info->group = g_strdup(throttle_group_get_name(blk));
}
info->write_threshold = bdrv_write_threshold_get(bs);
bs0 = bs;
p_image_info = &info->image;
info->backing_file_depth = 0;
while (1) {
Error *local_err = NULL;
bdrv_query_image_info(bs0, p_image_info, &local_err);
if (local_err) {
error_propagate(errp, local_err);
qapi_free_BlockDeviceInfo(info);
return NULL;
}
if (bs0->drv && bs0->backing) {
info->backing_file_depth++;
bs0 = bs0->backing->bs;
(*p_image_info)->has_backing_image = true;
p_image_info = &((*p_image_info)->backing_image);
} else {
break;
}
/* Skip automatically inserted nodes that the user isn't aware of for
* query-block (blk != NULL), but not for query-named-block-nodes */
while (blk && bs0->drv && bs0->implicit) {
bs0 = backing_bs(bs0);
assert(bs0);
}
}
return info;
}
/*
* Returns 0 on success, with *p_list either set to describe snapshot
* information, or NULL because there are no snapshots. Returns -errno on
* error, with *p_list untouched.
*/
int bdrv_query_snapshot_info_list(BlockDriverState *bs,
SnapshotInfoList **p_list,
Error **errp)
{
int i, sn_count;
QEMUSnapshotInfo *sn_tab = NULL;
SnapshotInfoList *info_list, *cur_item = NULL, *head = NULL;
SnapshotInfo *info;
sn_count = bdrv_snapshot_list(bs, &sn_tab);
if (sn_count < 0) {
const char *dev = bdrv_get_device_name(bs);
switch (sn_count) {
case -ENOMEDIUM:
error_setg(errp, "Device '%s' is not inserted", dev);
break;
case -ENOTSUP:
error_setg(errp,
"Device '%s' does not support internal snapshots",
dev);
break;
default:
error_setg_errno(errp, -sn_count,
"Can't list snapshots of device '%s'", dev);
break;
}
return sn_count;
}
for (i = 0; i < sn_count; i++) {
info = g_new0(SnapshotInfo, 1);
info->id = g_strdup(sn_tab[i].id_str);
info->name = g_strdup(sn_tab[i].name);
info->vm_state_size = sn_tab[i].vm_state_size;
info->date_sec = sn_tab[i].date_sec;
info->date_nsec = sn_tab[i].date_nsec;
info->vm_clock_sec = sn_tab[i].vm_clock_nsec / 1000000000;
info->vm_clock_nsec = sn_tab[i].vm_clock_nsec % 1000000000;
info_list = g_new0(SnapshotInfoList, 1);
info_list->value = info;
/* XXX: waiting for the qapi to support qemu-queue.h types */
if (!cur_item) {
head = cur_item = info_list;
} else {
cur_item->next = info_list;
cur_item = info_list;
}
}
g_free(sn_tab);
*p_list = head;
return 0;
}
void stream_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, const char *backing_file_str,
int creation_flags, int64_t speed,
BlockdevOnError on_error, Error **errp)
{
StreamBlockJob *s;
BlockDriverState *iter;
bool bs_read_only;
if (bdrv_freeze_backing_chain(bs, base, errp) < 0) {
return;
}
/* Make sure that the image is opened in read-write mode */
bs_read_only = bdrv_is_read_only(bs);
if (bs_read_only) {
if (bdrv_reopen_set_read_only(bs, false, errp) != 0) {
bs_read_only = false;
goto fail;
}
}
/* Prevent concurrent jobs trying to modify the graph structure here, we
* already have our own plans. Also don't allow resize as the image size is
* queried only at the job start and then cached. */
s = block_job_create(job_id, &stream_job_driver, NULL, bs,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_GRAPH_MOD,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_WRITE,
speed, creation_flags, NULL, NULL, errp);
if (!s) {
goto fail;
}
/* Block all intermediate nodes between bs and base, because they will
* disappear from the chain after this operation. The streaming job reads
* every block only once, assuming that it doesn't change, so block writes
* and resizes. */
for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
&error_abort);
}
s->base = base;
s->backing_file_str = g_strdup(backing_file_str);
s->bs_read_only = bs_read_only;
s->chain_frozen = true;
s->on_error = on_error;
trace_stream_start(bs, base, s);
job_start(&s->common.job);
return;
fail:
if (bs_read_only) {
bdrv_reopen_set_read_only(bs, true, NULL);
}
bdrv_unfreeze_backing_chain(bs, base);
}
static int coroutine_fn stream_run(Job *job, Error **errp)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
BlockBackend *blk = s->common.blk;
BlockDriverState *bs = blk_bs(blk);
BlockDriverState *base = s->base;
int64_t len;
int64_t offset = 0;
uint64_t delay_ns = 0;
int error = 0;
int ret = 0;
int64_t n = 0; /* bytes */
void *buf;
if (!bs->backing) {
goto out;
}
len = bdrv_getlength(bs);
if (len < 0) {
ret = len;
goto out;
}
job_progress_set_remaining(&s->common.job, len);
buf = qemu_blockalign(bs, STREAM_BUFFER_SIZE);
/* Turn on copy-on-read for the whole block device so that guest read
* requests help us make progress. Only do this when copying the entire
* backing chain since the copy-on-read operation does not take base into
* account.
*/
if (!base) {
bdrv_enable_copy_on_read(bs);
}
for ( ; offset < len; offset += n) {
bool copy;
/* Note that even when no rate limit is applied we need to yield
* with no pending I/O here so that bdrv_drain_all() returns.
*/
job_sleep_ns(&s->common.job, delay_ns);
if (job_is_cancelled(&s->common.job)) {
break;
}
copy = false;
ret = bdrv_is_allocated(bs, offset, STREAM_BUFFER_SIZE, &n);
if (ret == 1) {
/* Allocated in the top, no need to copy. */
} else if (ret >= 0) {
/* Copy if allocated in the intermediate images. Limit to the
* known-unallocated area [offset, offset+n*BDRV_SECTOR_SIZE). */
ret = bdrv_is_allocated_above(backing_bs(bs), base,
offset, n, &n);
/* Finish early if end of backing file has been reached */
if (ret == 0 && n == 0) {
n = len - offset;
}
copy = (ret == 1);
}
trace_stream_one_iteration(s, offset, n, ret);
if (copy) {
ret = stream_populate(blk, offset, n, buf);
}
if (ret < 0) {
BlockErrorAction action =
block_job_error_action(&s->common, s->on_error, true, -ret);
if (action == BLOCK_ERROR_ACTION_STOP) {
n = 0;
continue;
}
if (error == 0) {
error = ret;
}
if (action == BLOCK_ERROR_ACTION_REPORT) {
break;
}
}
ret = 0;
/* Publish progress */
job_progress_update(&s->common.job, n);
if (copy) {
delay_ns = block_job_ratelimit_get_delay(&s->common, n);
} else {
delay_ns = 0;
}
}
if (!base) {
bdrv_disable_copy_on_read(bs);
}
/* Do not remove the backing file if an error was there but ignored. */
ret = error;
qemu_vfree(buf);
out:
/* Modify backing chain and close BDSes in main loop */
return ret;
}
/* 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);
}
}
