void commit_active_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, int creation_flags,
int64_t speed, BlockdevOnError on_error,
const char *filter_node_name,
BlockCompletionFunc *cb, void *opaque,
bool auto_complete, Error **errp)
{
int orig_base_flags;
Error *local_err = NULL;
orig_base_flags = bdrv_get_flags(base);
if (bdrv_reopen(base, bs->open_flags, errp)) {
return;
}
mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0,
MIRROR_LEAVE_BACKING_CHAIN,
on_error, on_error, true, cb, opaque,
&commit_active_job_driver, false, base, auto_complete,
filter_node_name, false, &local_err);
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;
}
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_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);
}
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);
}
static inline bool can_write(BlockDriverState *bs)
{
return !bdrv_is_read_only(bs) && !(bdrv_get_flags(bs) & BDRV_O_INACTIVE);
}
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) {
block_job_completed(&s->common, s->common.len);
return;
}
length = (bdrv_getlength(bs) + s->granularity - 1) / 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) {
bdrv_get_info(s->target, &bdi);
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->mode != MIRROR_SYNC_MODE_NONE) {
/* First part, loop on the sectors and initialize the dirty bitmap. */
BlockDriverState *base;
base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
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->hbi);
last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
for (;;) {
uint64_t delay_ns;
int64_t cnt;
bool should_complete;
if (s->ret < 0) {
ret = s->ret;
goto immediate_exit;
}
cnt = bdrv_get_dirty_count(bs);
/* 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) {
mirror_iteration(s);
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) == BDRV_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_ready(&s->common);
s->synced = true;
}
should_complete = s->should_complete ||
block_job_is_cancelled(&s->common);
cnt = bdrv_get_dirty_count(bs);
}
}
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);
}
ret = 0;
trace_mirror_before_sleep(s, cnt, s->synced);
if (!s->synced) {
/* Publish progress */
s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
if (s->common.speed) {
delay_ns = ratelimit_calculate_delay(&s->limit, sectors_per_chunk);
} else {
delay_ns = 0;
}
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_set_dirty_tracking(bs, 0);
bdrv_iostatus_disable(s->target);
if (s->should_complete && ret == 0) {
if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
}
bdrv_swap(s->target, s->common.bs);
}
bdrv_close(s->target);
bdrv_unref(s->target);
block_job_completed(&s->common, ret);
}
static void coroutine_fn commit_run(void *opaque)
{
CommitBlockJob *s = opaque;
BlockDriverState *active = s->active;
BlockDriverState *top = s->top;
BlockDriverState *base = s->base;
BlockDriverState *overlay_bs = NULL;
int64_t sector_num, end;
int ret = 0;
int n = 0;
void *buf;
int bytes_written = 0;
int64_t base_len;
ret = s->common.len = bdrv_getlength(top);
if (s->common.len < 0) {
goto exit_restore_reopen;
}
ret = base_len = bdrv_getlength(base);
if (base_len < 0) {
goto exit_restore_reopen;
}
if (base_len < s->common.len) {
ret = bdrv_truncate(base, s->common.len);
if (ret) {
goto exit_restore_reopen;
}
}
overlay_bs = bdrv_find_overlay(active, top);
end = s->common.len >> BDRV_SECTOR_BITS;
buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);
for (sector_num = 0; sector_num < end; sector_num += n) {
uint64_t delay_ms = 0;
bool copy;
wait:
/* Note that even when no rate limit is applied we need to yield
* with no pending I/O here so that qemu_aio_flush() returns.
*/
block_job_sleep(&s->common, rt_clock, delay_ms);
if (block_job_is_cancelled(&s->common)) {
break;
}
/* Copy if allocated above the base */
ret = bdrv_co_is_allocated_above(top, base, sector_num,
COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
&n);
copy = (ret == 1);
trace_commit_one_iteration(s, sector_num, n, ret);
if (copy) {
if (s->common.speed) {
delay_ms = ratelimit_calculate_delay(&s->limit, n);
if (delay_ms > 0) {
goto wait;
}
}
ret = commit_populate(top, base, sector_num, n, buf);
bytes_written += n * BDRV_SECTOR_SIZE;
}
if (ret < 0) {
if (s->on_error == BLOCK_ERR_STOP_ANY ||
s->on_error == BLOCK_ERR_REPORT ||
(s->on_error == BLOCK_ERR_STOP_ENOSPC && ret == -ENOSPC)) {
goto exit_free_buf;
} else {
n = 0;
continue;
}
}
/* Publish progress */
s->common.offset += n * BDRV_SECTOR_SIZE;
}
ret = 0;
if (!block_job_is_cancelled(&s->common) && sector_num == end) {
/* success */
ret = bdrv_drop_intermediate(active, top, base);
}
exit_free_buf:
qemu_vfree(buf);
exit_restore_reopen:
/* restore base open flags here if appropriate (e.g., change the base back
* to r/o). These reopens do not need to be atomic, since we won't abort
* even on failure here */
if (s->base_flags != bdrv_get_flags(base)) {
bdrv_reopen(base, s->base_flags, NULL);
}
if (s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
}
block_job_complete(&s->common, ret);
}
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockErrorAction on_error, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
CommitBlockJob *s;
BlockReopenQueue *reopen_queue = NULL;
int orig_overlay_flags;
int orig_base_flags;
BlockDriverState *overlay_bs;
Error *local_err = NULL;
if ((on_error == BLOCK_ERR_STOP_ANY ||
on_error == BLOCK_ERR_STOP_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
return;
}
/* Once we support top == active layer, remove this check */
if (top == bs) {
error_set(errp, QERR_TOP_IS_ACTIVE);
return;
}
if (top == base) {
error_set(errp, QERR_TOP_AND_BASE_IDENTICAL);
return;
}
overlay_bs = bdrv_find_overlay(bs, top);
if (overlay_bs == NULL) {
error_set(errp, QERR_TOP_NOT_FOUND, top->filename);
return;
}
orig_base_flags = bdrv_get_flags(base);
orig_overlay_flags = bdrv_get_flags(overlay_bs);
/* convert base & overlay_bs to r/w, if necessary */
if (!(orig_base_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, base,
orig_base_flags | BDRV_O_RDWR);
}
if (!(orig_overlay_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
orig_overlay_flags | BDRV_O_RDWR);
}
if (reopen_queue) {
bdrv_reopen_multiple(reopen_queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
return;
}
}
s = block_job_create(&commit_job_type, bs, speed, cb, opaque);
if (!s) {
error_set(errp, QERR_DEVICE_IN_USE, bs->device_name);
return;
}
s->base = base;
s->top = top;
s->active = bs;
s->base_flags = orig_base_flags;
s->orig_overlay_flags = orig_overlay_flags;
s->on_error = on_error;
s->common.co = qemu_coroutine_create(commit_run);
trace_commit_start(bs, base, top, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
}
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
CommitBlockJob *s;
BlockReopenQueue *reopen_queue = NULL;
int orig_overlay_flags;
int orig_base_flags;
BlockDriverState *overlay_bs;
Error *local_err = NULL;
if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
return;
}
/* Once we support top == active layer, remove this check */
if (top == bs) {
error_setg(errp,
"Top image as the active layer is currently unsupported");
return;
}
if (top == base) {
error_setg(errp, "Invalid files for merge: top and base are the same");
return;
}
overlay_bs = bdrv_find_overlay(bs, top);
if (overlay_bs == NULL) {
error_setg(errp, "Could not find overlay image for %s:", top->filename);
return;
}
orig_base_flags = bdrv_get_flags(base);
orig_overlay_flags = bdrv_get_flags(overlay_bs);
/* convert base & overlay_bs to r/w, if necessary */
if (!(orig_base_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, base,
orig_base_flags | BDRV_O_RDWR);
}
if (!(orig_overlay_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
orig_overlay_flags | BDRV_O_RDWR);
}
if (reopen_queue) {
bdrv_reopen_multiple(reopen_queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
return;
}
}
s = block_job_create(&commit_job_type, bs, speed, cb, opaque, errp);
if (!s) {
return;
}
s->base = base;
s->top = top;
s->active = bs;
s->base_flags = orig_base_flags;
s->orig_overlay_flags = orig_overlay_flags;
s->on_error = on_error;
s->common.co = qemu_coroutine_create(commit_run);
trace_commit_start(bs, base, top, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
}
