static int stream_prepare(Job *job)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
BlockJob *bjob = &s->common;
BlockDriverState *bs = blk_bs(bjob->blk);
BlockDriverState *base = s->base;
Error *local_err = NULL;
int ret = 0;
bdrv_unfreeze_backing_chain(bs, base);
s->chain_frozen = false;
if (bs->backing) {
const char *base_id = NULL, *base_fmt = NULL;
if (base) {
base_id = s->backing_file_str;
if (base->drv) {
base_fmt = base->drv->format_name;
}
}
ret = bdrv_change_backing_file(bs, base_id, base_fmt);
bdrv_set_backing_hd(bs, base, &local_err);
if (local_err) {
error_report_err(local_err);
return -EPERM;
}
}
return ret;
}
static void mirror_exit(BlockJob *job, void *opaque)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
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_swap(s->target, to_replace);
if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
/* drop the bs loop chain formed by the swap: break the loop then
* trigger the unref from the top one */
BlockDriverState *p = s->base->backing_hd;
bdrv_set_backing_hd(s->base, NULL);
bdrv_unref(p);
}
}
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(s->target);
block_job_completed(&s->common, data->ret);
g_free(data);
}
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);
}
/* 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);
}
}
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, sectors_per_chunk, length;
uint64_t last_pause_ns;
BlockDriverInfo bdi;
char backing_filename[1024];
int ret = 0;
int n;
if (block_job_is_cancelled(&s->common)) {
goto immediate_exit;
}
s->common.len = bdrv_getlength(bs);
if (s->common.len < 0) {
ret = s->common.len;
goto immediate_exit;
} else if (s->common.len == 0) {
/* Report BLOCK_JOB_READY and wait for complete. */
block_job_event_ready(&s->common);
s->synced = true;
while (!block_job_is_cancelled(&s->common) && !s->should_complete) {
block_job_yield(&s->common);
}
s->common.cancelled = false;
goto immediate_exit;
}
length = DIV_ROUND_UP(s->common.len, s->granularity);
s->in_flight_bitmap = bitmap_new(length);
/* If we have no backing file yet in the destination, we cannot let
* the destination do COW. Instead, we copy sectors around the
* dirty data if needed. We need a bitmap to do that.
*/
bdrv_get_backing_filename(s->target, backing_filename,
sizeof(backing_filename));
if (backing_filename[0] && !s->target->backing_hd) {
ret = bdrv_get_info(s->target, &bdi);
if (ret < 0) {
goto immediate_exit;
}
if (s->granularity < bdi.cluster_size) {
s->buf_size = MAX(s->buf_size, bdi.cluster_size);
s->cow_bitmap = bitmap_new(length);
}
}
end = s->common.len >> BDRV_SECTOR_BITS;
s->buf = qemu_blockalign(bs, s->buf_size);
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
mirror_free_init(s);
if (!s->is_none_mode) {
/* First part, loop on the sectors and initialize the dirty bitmap. */
BlockDriverState *base = s->base;
for (sector_num = 0; sector_num < end; ) {
int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
ret = bdrv_is_allocated_above(bs, base,
sector_num, next - sector_num, &n);
if (ret < 0) {
goto immediate_exit;
}
assert(n > 0);
if (ret == 1) {
bdrv_set_dirty(bs, sector_num, n);
sector_num = next;
} else {
sector_num += n;
}
}
}
bdrv_dirty_iter_init(bs, s->dirty_bitmap, &s->hbi);
last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
for (;;) {
uint64_t delay_ns = 0;
int64_t cnt;
bool should_complete;
if (s->ret < 0) {
ret = s->ret;
goto immediate_exit;
}
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
/* Note that even when no rate limit is applied we need to yield
* periodically with no pending I/O so that qemu_aio_flush() returns.
* We do so every SLICE_TIME nanoseconds, or when there is an error,
* or when the source is clean, whichever comes first.
*/
if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - last_pause_ns < SLICE_TIME &&
s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
(cnt == 0 && s->in_flight > 0)) {
trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
qemu_coroutine_yield();
continue;
} else if (cnt != 0) {
delay_ns = mirror_iteration(s);
if (delay_ns == 0) {
continue;
}
}
}
should_complete = false;
if (s->in_flight == 0 && cnt == 0) {
trace_mirror_before_flush(s);
ret = bdrv_flush(s->target);
if (ret < 0) {
if (mirror_error_action(s, false, -ret) ==
BLOCK_ERROR_ACTION_REPORT) {
goto immediate_exit;
}
} else {
/* We're out of the streaming phase. From now on, if the job
* is cancelled we will actually complete all pending I/O and
* report completion. This way, block-job-cancel will leave
* the target in a consistent state.
*/
s->common.offset = end * BDRV_SECTOR_SIZE;
if (!s->synced) {
block_job_event_ready(&s->common);
s->synced = true;
}
should_complete = s->should_complete ||
block_job_is_cancelled(&s->common);
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
}
}
if (cnt == 0 && should_complete) {
/* The dirty bitmap is not updated while operations are pending.
* If we're about to exit, wait for pending operations before
* calling bdrv_get_dirty_count(bs), or we may exit while the
* source has dirty data to copy!
*
* Note that I/O can be submitted by the guest while
* mirror_populate runs.
*/
trace_mirror_before_drain(s, cnt);
bdrv_drain_all();
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
}
ret = 0;
trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
if (!s->synced) {
/* Publish progress */
s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
if (block_job_is_cancelled(&s->common)) {
break;
}
} else if (!should_complete) {
delay_ns = (s->in_flight == 0 && cnt == 0 ? SLICE_TIME : 0);
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
} else if (cnt == 0) {
/* The two disks are in sync. Exit and report successful
* completion.
*/
assert(QLIST_EMPTY(&bs->tracked_requests));
s->common.cancelled = false;
break;
}
last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
}
immediate_exit:
if (s->in_flight > 0) {
/* We get here only if something went wrong. Either the job failed,
* or it was cancelled prematurely so that we do not guarantee that
* the target is a copy of the source.
*/
assert(ret < 0 || (!s->synced && block_job_is_cancelled(&s->common)));
mirror_drain(s);
}
assert(s->in_flight == 0);
qemu_vfree(s->buf);
g_free(s->cow_bitmap);
g_free(s->in_flight_bitmap);
bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
bdrv_iostatus_disable(s->target);
if (s->should_complete && 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_swap(s->target, to_replace);
if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
/* drop the bs loop chain formed by the swap: break the loop then
* trigger the unref from the top one */
BlockDriverState *p = s->base->backing_hd;
bdrv_set_backing_hd(s->base, NULL);
bdrv_unref(p);
}
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
g_free(s->replaces);
bdrv_unref(s->target);
block_job_completed(&s->common, ret);
}
