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;
}
/* Round offset and/or bytes to target cluster if COW is needed, and
* return the offset of the adjusted tail against original. */
static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset,
uint64_t *bytes)
{
bool need_cow;
int ret = 0;
int64_t align_offset = *offset;
int64_t align_bytes = *bytes;
int max_bytes = s->granularity * s->max_iov;
need_cow = !test_bit(*offset / s->granularity, s->cow_bitmap);
need_cow |= !test_bit((*offset + *bytes - 1) / s->granularity,
s->cow_bitmap);
if (need_cow) {
bdrv_round_to_clusters(blk_bs(s->target), *offset, *bytes,
&align_offset, &align_bytes);
}
if (align_bytes > max_bytes) {
align_bytes = max_bytes;
if (need_cow) {
align_bytes = QEMU_ALIGN_DOWN(align_bytes, s->target_cluster_size);
}
}
/* Clipping may result in align_bytes unaligned to chunk boundary, but
* that doesn't matter because it's already the end of source image. */
align_bytes = mirror_clip_bytes(s, align_offset, align_bytes);
ret = align_offset + align_bytes - (*offset + *bytes);
*offset = align_offset;
*bytes = align_bytes;
assert(ret >= 0);
return ret;
}
static void stream_abort(Job *job)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
if (s->chain_frozen) {
BlockJob *bjob = &s->common;
bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->base);
}
}
/* @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);
BlockDriverState *bs0;
ImageInfo **p_image_info;
Error *local_err = NULL;
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);
if (blk_dev_has_removable_media(blk)) {
info->has_tray_open = true;
info->tray_open = blk_dev_is_tray_open(blk);
}
if (bdrv_iostatus_is_enabled(bs)) {
info->has_io_status = true;
info->io_status = bs->iostatus;
}
if (!QLIST_EMPTY(&bs->dirty_bitmaps)) {
info->has_dirty_bitmaps = true;
info->dirty_bitmaps = bdrv_query_dirty_bitmaps(bs);
}
if (bs->drv) {
info->has_inserted = true;
info->inserted = bdrv_block_device_info(bs);
bs0 = bs;
p_image_info = &info->inserted->image;
while (1) {
bdrv_query_image_info(bs0, p_image_info, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto err;
}
if (bs0->drv && bs0->backing_hd) {
bs0 = bs0->backing_hd;
(*p_image_info)->has_backing_image = true;
p_image_info = &((*p_image_info)->backing_image);
} else {
break;
}
}
}
*p_info = info;
return;
err:
qapi_free_BlockInfo(info);
}
/* @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 void test_block_job_complete(BlockJob *job, void *opaque)
{
BlockDriverState *bs = blk_bs(job->blk);
int rc = (intptr_t)opaque;
if (block_job_is_cancelled(job)) {
rc = -ECANCELED;
}
block_job_completed(job, rc);
bdrv_unref(bs);
}
static char *print_drive(void *ptr)
{
const char *name;
name = blk_name(ptr);
if (!*name) {
BlockDriverState *bs = blk_bs(ptr);
if (bs) {
name = bdrv_get_node_name(bs);
}
}
return g_strdup(name);
}
static bool next_query_bds(BlockBackend **blk, BlockDriverState **bs,
bool query_nodes)
{
if (query_nodes) {
*bs = bdrv_next_node(*bs);
return !!*bs;
}
*blk = blk_next(*blk);
*bs = *blk ? blk_bs(*blk) : NULL;
return !!*blk;
}
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 stream_clean(Job *job)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
BlockJob *bjob = &s->common;
BlockDriverState *bs = blk_bs(bjob->blk);
/* Reopen the image back in read-only mode if necessary */
if (s->bs_read_only) {
/* Give up write permissions before making it read-only */
blk_set_perm(bjob->blk, 0, BLK_PERM_ALL, &error_abort);
bdrv_reopen_set_read_only(bs, true, NULL);
}
g_free(s->backing_file_str);
}
void qdev_prop_set_drive(DeviceState *dev, const char *name,
BlockBackend *value, Error **errp)
{
const char *ref = "";
if (value) {
ref = blk_name(value);
if (!*ref) {
BlockDriverState *bs = blk_bs(value);
if (bs) {
ref = bdrv_get_node_name(bs);
}
}
}
object_property_set_str(OBJECT(dev), ref, name, errp);
}
static BlockJob *do_test_id(BlockBackend *blk, const char *id,
bool should_succeed)
{
BlockJob *job;
Error *errp = NULL;
job = block_job_create(id, &test_block_job_driver, blk_bs(blk),
0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT, block_job_cb,
NULL, &errp);
if (should_succeed) {
g_assert_null(errp);
g_assert_nonnull(job);
if (id) {
g_assert_cmpstr(job->id, ==, id);
} else {
g_assert_cmpstr(job->id, ==, blk_name(blk));
}
} else {
static void test_sync_op_blk_flush(BlockBackend *blk)
{
BlockDriverState *bs = blk_bs(blk);
int ret;
/* Normal success path */
ret = blk_flush(blk);
g_assert_cmpint(ret, ==, 0);
/* Early success: Read-only image */
bs->read_only = true;
bs->open_flags &= ~BDRV_O_RDWR;
ret = blk_flush(blk);
g_assert_cmpint(ret, ==, 0);
bs->read_only = false;
bs->open_flags |= BDRV_O_RDWR;
}
BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
bool query_nodes,
Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockBackend *blk;
BlockDriverState *bs;
/* Just to be safe if query_nodes is not always initialized */
if (has_query_nodes && query_nodes) {
for (bs = bdrv_next_node(NULL); bs; bs = bdrv_next_node(bs)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_bds_stats(bs, false);
aio_context_release(ctx);
*p_next = info;
p_next = &info->next;
}
} else {
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk_get_aio_context(blk);
BlockStats *s;
aio_context_acquire(ctx);
s = bdrv_query_bds_stats(blk_bs(blk), true);
s->has_device = true;
s->device = g_strdup(blk_name(blk));
bdrv_query_blk_stats(s->stats, blk);
aio_context_release(ctx);
info->value = s;
*p_next = info;
p_next = &info->next;
}
}
return head;
}
/* @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);
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);
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 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 coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
MirrorExitData *data;
BlockDriverState *bs = s->source;
BlockDriverState *target_bs = blk_bs(s->target);
bool need_drain = true;
int64_t length;
BlockDriverInfo bdi;
char backing_filename[2]; /* we only need 2 characters because we are only
checking for a NULL string */
int ret = 0;
if (block_job_is_cancelled(&s->common)) {
goto immediate_exit;
}
s->bdev_length = bdrv_getlength(bs);
if (s->bdev_length < 0) {
ret = s->bdev_length;
goto immediate_exit;
}
/* Active commit must resize the base image if its size differs from the
* active layer. */
if (s->base == blk_bs(s->target)) {
int64_t base_length;
base_length = blk_getlength(s->target);
if (base_length < 0) {
ret = base_length;
goto immediate_exit;
}
if (s->bdev_length > base_length) {
ret = blk_truncate(s->target, s->bdev_length, PREALLOC_MODE_OFF,
NULL);
if (ret < 0) {
goto immediate_exit;
}
}
}
if (s->bdev_length == 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->bdev_length, 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(target_bs, backing_filename,
sizeof(backing_filename));
if (!bdrv_get_info(target_bs, &bdi) && bdi.cluster_size) {
s->target_cluster_size = bdi.cluster_size;
} else {
s->target_cluster_size = BDRV_SECTOR_SIZE;
}
if (backing_filename[0] && !target_bs->backing &&
s->granularity < s->target_cluster_size) {
s->buf_size = MAX(s->buf_size, s->target_cluster_size);
s->cow_bitmap = bitmap_new(length);
}
s->max_iov = MIN(bs->bl.max_iov, target_bs->bl.max_iov);
s->buf = qemu_try_blockalign(bs, s->buf_size);
if (s->buf == NULL) {
ret = -ENOMEM;
goto immediate_exit;
}
mirror_free_init(s);
s->last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
if (!s->is_none_mode) {
ret = mirror_dirty_init(s);
if (ret < 0 || block_job_is_cancelled(&s->common)) {
goto immediate_exit;
}
}
assert(!s->dbi);
s->dbi = bdrv_dirty_iter_new(s->dirty_bitmap);
for (;;) {
uint64_t delay_ns = 0;
int64_t cnt, delta;
bool should_complete;
if (s->ret < 0) {
ret = s->ret;
goto immediate_exit;
}
block_job_pause_point(&s->common);
cnt = bdrv_get_dirty_count(s->dirty_bitmap);
/* cnt is the number of dirty bytes remaining and s->bytes_in_flight is
* the number of bytes currently being processed; together those are
* the current remaining operation length */
block_job_progress_set_remaining(&s->common, s->bytes_in_flight + cnt);
/* Note that even when no rate limit is applied we need to yield
* periodically with no pending I/O so that bdrv_drain_all() returns.
* We do so every BLKOCK_JOB_SLICE_TIME nanoseconds, or when there is
* an error, or when the source is clean, whichever comes first. */
delta = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - s->last_pause_ns;
if (delta < BLOCK_JOB_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, cnt, s->buf_free_count, s->in_flight);
mirror_wait_for_io(s);
continue;
} else if (cnt != 0) {
delay_ns = mirror_iteration(s);
}
}
should_complete = false;
if (s->in_flight == 0 && cnt == 0) {
trace_mirror_before_flush(s);
if (!s->synced) {
if (mirror_flush(s) < 0) {
/* Go check s->ret. */
continue;
}
/* 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.
*/
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(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, so pause it now. Before deciding
* whether to switch to target check one last time if I/O has
* come in the meanwhile, and if not flush the data to disk.
*/
trace_mirror_before_drain(s, cnt);
bdrv_drained_begin(bs);
cnt = bdrv_get_dirty_count(s->dirty_bitmap);
if (cnt > 0 || mirror_flush(s) < 0) {
bdrv_drained_end(bs);
continue;
}
/* The two disks are in sync. Exit and report successful
* completion.
*/
assert(QLIST_EMPTY(&bs->tracked_requests));
s->common.cancelled = false;
need_drain = false;
break;
}
ret = 0;
if (s->synced && !should_complete) {
delay_ns = (s->in_flight == 0 &&
cnt == 0 ? BLOCK_JOB_SLICE_TIME : 0);
}
trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
block_job_sleep_ns(&s->common, delay_ns);
if (block_job_is_cancelled(&s->common) &&
(!s->synced || s->common.force))
{
break;
}
s->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->common.force || !s->synced) &&
block_job_is_cancelled(&s->common)));
assert(need_drain);
mirror_wait_for_all_io(s);
}
assert(s->in_flight == 0);
qemu_vfree(s->buf);
g_free(s->cow_bitmap);
g_free(s->in_flight_bitmap);
bdrv_dirty_iter_free(s->dbi);
data = g_malloc(sizeof(*data));
data->ret = ret;
if (need_drain) {
bdrv_drained_begin(bs);
}
block_job_defer_to_main_loop(&s->common, mirror_exit, data);
}
static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
{
int64_t offset;
BlockDriverState *base = s->base;
BlockDriverState *bs = s->source;
BlockDriverState *target_bs = blk_bs(s->target);
int ret;
int64_t count;
if (base == NULL && !bdrv_has_zero_init(target_bs)) {
if (!bdrv_can_write_zeroes_with_unmap(target_bs)) {
bdrv_set_dirty_bitmap(s->dirty_bitmap, 0, s->bdev_length);
return 0;
}
s->initial_zeroing_ongoing = true;
for (offset = 0; offset < s->bdev_length; ) {
int bytes = MIN(s->bdev_length - offset,
QEMU_ALIGN_DOWN(INT_MAX, s->granularity));
mirror_throttle(s);
if (block_job_is_cancelled(&s->common)) {
s->initial_zeroing_ongoing = false;
return 0;
}
if (s->in_flight >= MAX_IN_FLIGHT) {
trace_mirror_yield(s, UINT64_MAX, s->buf_free_count,
s->in_flight);
mirror_wait_for_io(s);
continue;
}
mirror_do_zero_or_discard(s, offset, bytes, false);
offset += bytes;
}
mirror_wait_for_all_io(s);
s->initial_zeroing_ongoing = false;
}
/* First part, loop on the sectors and initialize the dirty bitmap. */
for (offset = 0; offset < s->bdev_length; ) {
/* Just to make sure we are not exceeding int limit. */
int bytes = MIN(s->bdev_length - offset,
QEMU_ALIGN_DOWN(INT_MAX, s->granularity));
mirror_throttle(s);
if (block_job_is_cancelled(&s->common)) {
return 0;
}
ret = bdrv_is_allocated_above(bs, base, offset, bytes, &count);
if (ret < 0) {
return ret;
}
assert(count);
if (ret == 1) {
bdrv_set_dirty_bitmap(s->dirty_bitmap, offset, count);
}
offset += count;
}
return 0;
}
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 uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
{
BlockDriverState *source = s->source;
int64_t offset, first_chunk;
uint64_t delay_ns = 0;
/* At least the first dirty chunk is mirrored in one iteration. */
int nb_chunks = 1;
bool write_zeroes_ok = bdrv_can_write_zeroes_with_unmap(blk_bs(s->target));
int max_io_bytes = MAX(s->buf_size / MAX_IN_FLIGHT, MAX_IO_BYTES);
bdrv_dirty_bitmap_lock(s->dirty_bitmap);
offset = bdrv_dirty_iter_next(s->dbi);
if (offset < 0) {
bdrv_set_dirty_iter(s->dbi, 0);
offset = bdrv_dirty_iter_next(s->dbi);
trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
assert(offset >= 0);
}
bdrv_dirty_bitmap_unlock(s->dirty_bitmap);
first_chunk = offset / s->granularity;
while (test_bit(first_chunk, s->in_flight_bitmap)) {
trace_mirror_yield_in_flight(s, offset, s->in_flight);
mirror_wait_for_io(s);
}
block_job_pause_point(&s->common);
/* Find the number of consective dirty chunks following the first dirty
* one, and wait for in flight requests in them. */
bdrv_dirty_bitmap_lock(s->dirty_bitmap);
while (nb_chunks * s->granularity < s->buf_size) {
int64_t next_dirty;
int64_t next_offset = offset + nb_chunks * s->granularity;
int64_t next_chunk = next_offset / s->granularity;
if (next_offset >= s->bdev_length ||
!bdrv_get_dirty_locked(source, s->dirty_bitmap, next_offset)) {
break;
}
if (test_bit(next_chunk, s->in_flight_bitmap)) {
break;
}
next_dirty = bdrv_dirty_iter_next(s->dbi);
if (next_dirty > next_offset || next_dirty < 0) {
/* The bitmap iterator's cache is stale, refresh it */
bdrv_set_dirty_iter(s->dbi, next_offset);
next_dirty = bdrv_dirty_iter_next(s->dbi);
}
assert(next_dirty == next_offset);
nb_chunks++;
}
/* Clear dirty bits before querying the block status, because
* calling bdrv_block_status_above could yield - if some blocks are
* marked dirty in this window, we need to know.
*/
bdrv_reset_dirty_bitmap_locked(s->dirty_bitmap, offset,
nb_chunks * s->granularity);
bdrv_dirty_bitmap_unlock(s->dirty_bitmap);
bitmap_set(s->in_flight_bitmap, offset / s->granularity, nb_chunks);
while (nb_chunks > 0 && offset < s->bdev_length) {
int ret;
int64_t io_bytes;
int64_t io_bytes_acct;
enum MirrorMethod {
MIRROR_METHOD_COPY,
MIRROR_METHOD_ZERO,
MIRROR_METHOD_DISCARD
} mirror_method = MIRROR_METHOD_COPY;
assert(!(offset % s->granularity));
ret = bdrv_block_status_above(source, NULL, offset,
nb_chunks * s->granularity,
&io_bytes, NULL, NULL);
if (ret < 0) {
io_bytes = MIN(nb_chunks * s->granularity, max_io_bytes);
} else if (ret & BDRV_BLOCK_DATA) {
io_bytes = MIN(io_bytes, max_io_bytes);
}
io_bytes -= io_bytes % s->granularity;
if (io_bytes < s->granularity) {
io_bytes = s->granularity;
} else if (ret >= 0 && !(ret & BDRV_BLOCK_DATA)) {
int64_t target_offset;
int64_t target_bytes;
bdrv_round_to_clusters(blk_bs(s->target), offset, io_bytes,
&target_offset, &target_bytes);
if (target_offset == offset &&
target_bytes == io_bytes) {
mirror_method = ret & BDRV_BLOCK_ZERO ?
MIRROR_METHOD_ZERO :
MIRROR_METHOD_DISCARD;
}
}
while (s->in_flight >= MAX_IN_FLIGHT) {
trace_mirror_yield_in_flight(s, offset, s->in_flight);
mirror_wait_for_io(s);
}
if (s->ret < 0) {
return 0;
}
io_bytes = mirror_clip_bytes(s, offset, io_bytes);
switch (mirror_method) {
case MIRROR_METHOD_COPY:
io_bytes = io_bytes_acct = mirror_do_read(s, offset, io_bytes);
break;
case MIRROR_METHOD_ZERO:
case MIRROR_METHOD_DISCARD:
mirror_do_zero_or_discard(s, offset, io_bytes,
mirror_method == MIRROR_METHOD_DISCARD);
if (write_zeroes_ok) {
io_bytes_acct = 0;
} else {
io_bytes_acct = io_bytes;
}
break;
default:
abort();
}
assert(io_bytes);
offset += io_bytes;
nb_chunks -= DIV_ROUND_UP(io_bytes, s->granularity);
delay_ns = block_job_ratelimit_get_delay(&s->common, io_bytes_acct);
}
return delay_ns;
}
static int blk_connect(struct XenDevice *xendev)
{
struct XenBlkDev *blkdev = container_of(xendev, struct XenBlkDev, xendev);
int index, qflags;
bool readonly = true;
bool writethrough = true;
int order, ring_ref;
unsigned int ring_size, max_grants;
unsigned int i;
trace_xen_disk_connect(xendev->name);
/* read-only ? */
if (blkdev->directiosafe) {
qflags = BDRV_O_NOCACHE | BDRV_O_NATIVE_AIO;
} else {
qflags = 0;
writethrough = false;
}
if (strcmp(blkdev->mode, "w") == 0) {
qflags |= BDRV_O_RDWR;
readonly = false;
}
if (blkdev->feature_discard) {
qflags |= BDRV_O_UNMAP;
}
/* init qemu block driver */
index = (xendev->dev - 202 * 256) / 16;
blkdev->dinfo = drive_get(IF_XEN, 0, index);
if (!blkdev->dinfo) {
Error *local_err = NULL;
QDict *options = NULL;
if (strcmp(blkdev->fileproto, "<unset>")) {
options = qdict_new();
qdict_put_str(options, "driver", blkdev->fileproto);
}
/* setup via xenbus -> create new block driver instance */
xen_pv_printf(xendev, 2, "create new bdrv (xenbus setup)\n");
blkdev->blk = blk_new_open(blkdev->filename, NULL, options,
qflags, &local_err);
if (!blkdev->blk) {
xen_pv_printf(xendev, 0, "error: %s\n",
error_get_pretty(local_err));
error_free(local_err);
return -1;
}
blk_set_enable_write_cache(blkdev->blk, !writethrough);
} else {
/* setup via qemu cmdline -> already setup for us */
xen_pv_printf(xendev, 2,
"get configured bdrv (cmdline setup)\n");
blkdev->blk = blk_by_legacy_dinfo(blkdev->dinfo);
if (blk_is_read_only(blkdev->blk) && !readonly) {
xen_pv_printf(xendev, 0, "Unexpected read-only drive");
blkdev->blk = NULL;
return -1;
}
/* blkdev->blk is not create by us, we get a reference
* so we can blk_unref() unconditionally */
blk_ref(blkdev->blk);
}
blk_attach_dev_legacy(blkdev->blk, blkdev);
blkdev->file_size = blk_getlength(blkdev->blk);
if (blkdev->file_size < 0) {
BlockDriverState *bs = blk_bs(blkdev->blk);
const char *drv_name = bs ? bdrv_get_format_name(bs) : NULL;
xen_pv_printf(xendev, 1, "blk_getlength: %d (%s) | drv %s\n",
(int)blkdev->file_size, strerror(-blkdev->file_size),
drv_name ?: "-");
blkdev->file_size = 0;
}
int main(int argc, char **argv)
{
BlockBackend *blk;
BlockDriverState *bs;
off_t dev_offset = 0;
uint32_t nbdflags = 0;
bool disconnect = false;
const char *bindto = "0.0.0.0";
const char *port = NULL;
char *sockpath = NULL;
char *device = NULL;
off_t fd_size;
QemuOpts *sn_opts = NULL;
const char *sn_id_or_name = NULL;
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:";
struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "bind", 1, NULL, 'b' },
{ "port", 1, NULL, 'p' },
{ "socket", 1, NULL, 'k' },
{ "offset", 1, NULL, 'o' },
{ "read-only", 0, NULL, 'r' },
{ "partition", 1, NULL, 'P' },
{ "connect", 1, NULL, 'c' },
{ "disconnect", 0, NULL, 'd' },
{ "snapshot", 0, NULL, 's' },
{ "load-snapshot", 1, NULL, 'l' },
{ "nocache", 0, NULL, 'n' },
{ "cache", 1, NULL, QEMU_NBD_OPT_CACHE },
{ "aio", 1, NULL, QEMU_NBD_OPT_AIO },
{ "discard", 1, NULL, QEMU_NBD_OPT_DISCARD },
{ "detect-zeroes", 1, NULL, QEMU_NBD_OPT_DETECT_ZEROES },
{ "shared", 1, NULL, 'e' },
{ "format", 1, NULL, 'f' },
{ "persistent", 0, NULL, 't' },
{ "verbose", 0, NULL, 'v' },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret = 0;
int fd;
bool seen_cache = false;
bool seen_discard = false;
bool seen_aio = false;
pthread_t client_thread;
const char *fmt = NULL;
Error *local_err = NULL;
BlockdevDetectZeroesOptions detect_zeroes = BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
QDict *options = NULL;
/* The client thread uses SIGTERM to interrupt the server. A signal
* handler ensures that "qemu-nbd -v -c" exits with a nice status code.
*/
struct sigaction sa_sigterm;
memset(&sa_sigterm, 0, sizeof(sa_sigterm));
sa_sigterm.sa_handler = termsig_handler;
sigaction(SIGTERM, &sa_sigterm, NULL);
qemu_init_exec_dir(argv[0]);
while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) {
switch (ch) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
optarg = (char *) "none";
/* fallthrough */
case QEMU_NBD_OPT_CACHE:
if (seen_cache) {
errx(EXIT_FAILURE, "-n and --cache can only be specified once");
}
seen_cache = true;
if (bdrv_parse_cache_flags(optarg, &flags) == -1) {
errx(EXIT_FAILURE, "Invalid cache mode `%s'", optarg);
}
break;
case QEMU_NBD_OPT_AIO:
if (seen_aio) {
errx(EXIT_FAILURE, "--aio can only be specified once");
}
seen_aio = true;
if (!strcmp(optarg, "native")) {
flags |= BDRV_O_NATIVE_AIO;
} else if (!strcmp(optarg, "threads")) {
/* this is the default */
} else {
errx(EXIT_FAILURE, "invalid aio mode `%s'", optarg);
}
break;
case QEMU_NBD_OPT_DISCARD:
if (seen_discard) {
errx(EXIT_FAILURE, "--discard can only be specified once");
}
seen_discard = true;
if (bdrv_parse_discard_flags(optarg, &flags) == -1) {
errx(EXIT_FAILURE, "Invalid discard mode `%s'", optarg);
}
break;
case QEMU_NBD_OPT_DETECT_ZEROES:
detect_zeroes =
qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
optarg,
BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_err);
if (local_err) {
errx(EXIT_FAILURE, "Failed to parse detect_zeroes mode: %s",
error_get_pretty(local_err));
}
if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
!(flags & BDRV_O_UNMAP)) {
errx(EXIT_FAILURE, "setting detect-zeroes to unmap is not allowed "
"without setting discard operation to unmap");
}
break;
case 'b':
bindto = optarg;
break;
case 'p':
port = optarg;
break;
case 'o':
dev_offset = strtoll (optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid offset `%s'", optarg);
}
if (dev_offset < 0) {
errx(EXIT_FAILURE, "Offset must be positive `%s'", optarg);
}
break;
case 'l':
if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
optarg, false);
if (!sn_opts) {
errx(EXIT_FAILURE, "Failed in parsing snapshot param `%s'",
optarg);
}
} else {
sn_id_or_name = optarg;
}
/* fall through */
case 'r':
nbdflags |= NBD_FLAG_READ_ONLY;
flags &= ~BDRV_O_RDWR;
break;
case 'P':
partition = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid partition `%s'", optarg);
}
if (partition < 1 || partition > 8) {
errx(EXIT_FAILURE, "Invalid partition %d", partition);
}
break;
case 'k':
sockpath = optarg;
if (sockpath[0] != '/') {
errx(EXIT_FAILURE, "socket path must be absolute\n");
}
break;
case 'd':
disconnect = true;
break;
case 'c':
device = optarg;
break;
case 'e':
shared = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid shared device number '%s'", optarg);
}
if (shared < 1) {
errx(EXIT_FAILURE, "Shared device number must be greater than 0\n");
}
break;
case 'f':
fmt = optarg;
break;
case 't':
persistent = 1;
break;
case 'v':
verbose = 1;
break;
case 'V':
version(argv[0]);
exit(0);
break;
case 'h':
usage(argv[0]);
exit(0);
break;
case '?':
errx(EXIT_FAILURE, "Try `%s --help' for more information.",
argv[0]);
}
}
if ((argc - optind) != 1) {
errx(EXIT_FAILURE, "Invalid number of argument.\n"
"Try `%s --help' for more information.",
argv[0]);
}
if (disconnect) {
fd = open(argv[optind], O_RDWR);
if (fd < 0) {
err(EXIT_FAILURE, "Cannot open %s", argv[optind]);
}
nbd_disconnect(fd);
close(fd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
if (device && !verbose) {
int stderr_fd[2];
pid_t pid;
int ret;
if (qemu_pipe(stderr_fd) < 0) {
err(EXIT_FAILURE, "Error setting up communication pipe");
}
/* Now daemonize, but keep a communication channel open to
* print errors and exit with the proper status code.
*/
pid = fork();
if (pid < 0) {
err(EXIT_FAILURE, "Failed to fork");
} else if (pid == 0) {
close(stderr_fd[0]);
ret = qemu_daemon(1, 0);
/* Temporarily redirect stderr to the parent's pipe... */
dup2(stderr_fd[1], STDERR_FILENO);
if (ret < 0) {
err(EXIT_FAILURE, "Failed to daemonize");
}
/* ... close the descriptor we inherited and go on. */
close(stderr_fd[1]);
} else {
bool errors = false;
char *buf;
/* In the parent. Print error messages from the child until
* it closes the pipe.
*/
close(stderr_fd[1]);
buf = g_malloc(1024);
while ((ret = read(stderr_fd[0], buf, 1024)) > 0) {
errors = true;
ret = qemu_write_full(STDERR_FILENO, buf, ret);
if (ret < 0) {
exit(EXIT_FAILURE);
}
}
if (ret < 0) {
err(EXIT_FAILURE, "Cannot read from daemon");
}
/* Usually the daemon should not print any message.
* Exit with zero status in that case.
*/
exit(errors);
}
}
if (device != NULL && sockpath == NULL) {
sockpath = g_malloc(128);
snprintf(sockpath, 128, SOCKET_PATH, basename(device));
}
saddr = nbd_build_socket_address(sockpath, bindto, port);
if (qemu_init_main_loop(&local_err)) {
error_report_err(local_err);
exit(EXIT_FAILURE);
}
bdrv_init();
atexit(bdrv_close_all);
if (fmt) {
options = qdict_new();
qdict_put(options, "driver", qstring_from_str(fmt));
}
srcpath = argv[optind];
blk = blk_new_open("hda", srcpath, NULL, options, flags, &local_err);
if (!blk) {
errx(EXIT_FAILURE, "Failed to blk_new_open '%s': %s", argv[optind],
error_get_pretty(local_err));
}
bs = blk_bs(blk);
if (sn_opts) {
ret = bdrv_snapshot_load_tmp(bs,
qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
&local_err);
} else if (sn_id_or_name) {
ret = bdrv_snapshot_load_tmp_by_id_or_name(bs, sn_id_or_name,
&local_err);
}
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE,
"Failed to load snapshot: %s",
error_get_pretty(local_err));
}
bs->detect_zeroes = detect_zeroes;
fd_size = blk_getlength(blk);
if (fd_size < 0) {
errx(EXIT_FAILURE, "Failed to determine the image length: %s",
strerror(-fd_size));
}
if (partition != -1) {
ret = find_partition(blk, partition, &dev_offset, &fd_size);
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE, "Could not find partition %d", partition);
}
}
exp = nbd_export_new(blk, dev_offset, fd_size, nbdflags, nbd_export_closed,
&local_err);
if (!exp) {
errx(EXIT_FAILURE, "%s", error_get_pretty(local_err));
}
fd = socket_listen(saddr, &local_err);
if (fd < 0) {
error_report_err(local_err);
return 1;
}
if (device) {
int ret;
ret = pthread_create(&client_thread, NULL, nbd_client_thread, device);
if (ret != 0) {
errx(EXIT_FAILURE, "Failed to create client thread: %s",
strerror(ret));
}
} else {
/* Shut up GCC warnings. */
memset(&client_thread, 0, sizeof(client_thread));
}
server_fd = fd;
nbd_update_server_fd_handler(fd);
/* now when the initialization is (almost) complete, chdir("/")
* to free any busy filesystems */
if (chdir("/") < 0) {
err(EXIT_FAILURE, "Could not chdir to root directory");
}
state = RUNNING;
do {
main_loop_wait(false);
if (state == TERMINATE) {
state = TERMINATING;
nbd_export_close(exp);
nbd_export_put(exp);
exp = NULL;
}
} while (state != TERMINATED);
blk_unref(blk);
if (sockpath) {
unlink(sockpath);
}
qemu_opts_del(sn_opts);
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
static int coroutine_fn commit_run(Job *job, Error **errp)
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
int64_t offset;
uint64_t delay_ns = 0;
int ret = 0;
int64_t n = 0; /* bytes */
void *buf = NULL;
int bytes_written = 0;
int64_t len, base_len;
ret = len = blk_getlength(s->top);
if (len < 0) {
goto out;
}
job_progress_set_remaining(&s->common.job, len);
ret = base_len = blk_getlength(s->base);
if (base_len < 0) {
goto out;
}
if (base_len < len) {
ret = blk_truncate(s->base, len, PREALLOC_MODE_OFF, NULL);
if (ret) {
goto out;
}
}
buf = blk_blockalign(s->top, COMMIT_BUFFER_SIZE);
for (offset = 0; 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 if allocated above the base */
ret = bdrv_is_allocated_above(blk_bs(s->top), blk_bs(s->base),
offset, COMMIT_BUFFER_SIZE, &n);
copy = (ret == 1);
trace_commit_one_iteration(s, offset, n, ret);
if (copy) {
ret = commit_populate(s->top, s->base, offset, n, buf);
bytes_written += n;
}
if (ret < 0) {
BlockErrorAction action =
block_job_error_action(&s->common, false, s->on_error, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT) {
goto out;
} else {
n = 0;
continue;
}
}
/* 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;
}
}
ret = 0;
out:
qemu_vfree(buf);
return ret;
}
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;
}
BlockDriverState *bs;
if (qemuio_blk) {
error_report("file open already, try 'help close'");
QDECREF(opts);
return 1;
}
qemuio_blk = blk_new_open(name, NULL, opts, flags, &local_err);
if (!qemuio_blk) {
error_reportf_err(local_err, "can't open%s%s: ",
name ? " device " : "", name ?: "");
return 1;
}
bs = blk_bs(qemuio_blk);
if (bdrv_is_encrypted(bs)) {
char password[256];
printf("Disk image '%s' is encrypted.\n", name);
if (qemu_read_password(password, sizeof(password)) < 0) {
error_report("No password given");
goto error;
}
if (bdrv_set_key(bs, password) < 0) {
error_report("invalid password");
goto error;
}
}
return 0;
int main(int argc, char **argv)
{
BlockBackend *blk;
BlockDriverState *bs;
off_t dev_offset = 0;
uint16_t nbdflags = 0;
bool disconnect = false;
const char *bindto = NULL;
const char *port = NULL;
char *sockpath = NULL;
char *device = NULL;
off_t fd_size;
QemuOpts *sn_opts = NULL;
const char *sn_id_or_name = NULL;
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:x:T:D:";
struct option lopt[] = {
{ "help", no_argument, NULL, 'h' },
{ "version", no_argument, NULL, 'V' },
{ "bind", required_argument, NULL, 'b' },
{ "port", required_argument, NULL, 'p' },
{ "socket", required_argument, NULL, 'k' },
{ "offset", required_argument, NULL, 'o' },
{ "read-only", no_argument, NULL, 'r' },
{ "partition", required_argument, NULL, 'P' },
{ "connect", required_argument, NULL, 'c' },
{ "disconnect", no_argument, NULL, 'd' },
{ "snapshot", no_argument, NULL, 's' },
{ "load-snapshot", required_argument, NULL, 'l' },
{ "nocache", no_argument, NULL, 'n' },
{ "cache", required_argument, NULL, QEMU_NBD_OPT_CACHE },
{ "aio", required_argument, NULL, QEMU_NBD_OPT_AIO },
{ "discard", required_argument, NULL, QEMU_NBD_OPT_DISCARD },
{ "detect-zeroes", required_argument, NULL,
QEMU_NBD_OPT_DETECT_ZEROES },
{ "shared", required_argument, NULL, 'e' },
{ "format", required_argument, NULL, 'f' },
{ "persistent", no_argument, NULL, 't' },
{ "verbose", no_argument, NULL, 'v' },
{ "object", required_argument, NULL, QEMU_NBD_OPT_OBJECT },
{ "export-name", required_argument, NULL, 'x' },
{ "description", required_argument, NULL, 'D' },
{ "tls-creds", required_argument, NULL, QEMU_NBD_OPT_TLSCREDS },
{ "image-opts", no_argument, NULL, QEMU_NBD_OPT_IMAGE_OPTS },
{ "trace", required_argument, NULL, 'T' },
{ "fork", no_argument, NULL, QEMU_NBD_OPT_FORK },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret = 0;
bool seen_cache = false;
bool seen_discard = false;
bool seen_aio = false;
pthread_t client_thread;
const char *fmt = NULL;
Error *local_err = NULL;
BlockdevDetectZeroesOptions detect_zeroes = BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
QDict *options = NULL;
const char *export_name = NULL;
const char *export_description = NULL;
const char *tlscredsid = NULL;
bool imageOpts = false;
bool writethrough = true;
char *trace_file = NULL;
bool fork_process = false;
int old_stderr = -1;
unsigned socket_activation;
/* The client thread uses SIGTERM to interrupt the server. A signal
* handler ensures that "qemu-nbd -v -c" exits with a nice status code.
*/
struct sigaction sa_sigterm;
memset(&sa_sigterm, 0, sizeof(sa_sigterm));
sa_sigterm.sa_handler = termsig_handler;
sigaction(SIGTERM, &sa_sigterm, NULL);
#ifdef CONFIG_POSIX
signal(SIGPIPE, SIG_IGN);
#endif
module_call_init(MODULE_INIT_TRACE);
qcrypto_init(&error_fatal);
module_call_init(MODULE_INIT_QOM);
qemu_add_opts(&qemu_object_opts);
qemu_add_opts(&qemu_trace_opts);
qemu_init_exec_dir(argv[0]);
while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) {
switch (ch) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
optarg = (char *) "none";
/* fallthrough */
case QEMU_NBD_OPT_CACHE:
if (seen_cache) {
error_report("-n and --cache can only be specified once");
exit(EXIT_FAILURE);
}
seen_cache = true;
if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) == -1) {
error_report("Invalid cache mode `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case QEMU_NBD_OPT_AIO:
if (seen_aio) {
error_report("--aio can only be specified once");
exit(EXIT_FAILURE);
}
seen_aio = true;
if (!strcmp(optarg, "native")) {
flags |= BDRV_O_NATIVE_AIO;
} else if (!strcmp(optarg, "threads")) {
/* this is the default */
} else {
error_report("invalid aio mode `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case QEMU_NBD_OPT_DISCARD:
if (seen_discard) {
error_report("--discard can only be specified once");
exit(EXIT_FAILURE);
}
seen_discard = true;
if (bdrv_parse_discard_flags(optarg, &flags) == -1) {
error_report("Invalid discard mode `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case QEMU_NBD_OPT_DETECT_ZEROES:
detect_zeroes =
qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
optarg,
BLOCKDEV_DETECT_ZEROES_OPTIONS__MAX,
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_err);
if (local_err) {
error_reportf_err(local_err,
"Failed to parse detect_zeroes mode: ");
exit(EXIT_FAILURE);
}
if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
!(flags & BDRV_O_UNMAP)) {
error_report("setting detect-zeroes to unmap is not allowed "
"without setting discard operation to unmap");
exit(EXIT_FAILURE);
}
break;
case 'b':
bindto = optarg;
break;
case 'p':
port = optarg;
break;
case 'o':
dev_offset = strtoll (optarg, &end, 0);
if (*end) {
error_report("Invalid offset `%s'", optarg);
exit(EXIT_FAILURE);
}
if (dev_offset < 0) {
error_report("Offset must be positive `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case 'l':
if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
optarg, false);
if (!sn_opts) {
error_report("Failed in parsing snapshot param `%s'",
optarg);
exit(EXIT_FAILURE);
}
} else {
sn_id_or_name = optarg;
}
/* fall through */
case 'r':
nbdflags |= NBD_FLAG_READ_ONLY;
flags &= ~BDRV_O_RDWR;
break;
case 'P':
partition = strtol(optarg, &end, 0);
if (*end) {
error_report("Invalid partition `%s'", optarg);
exit(EXIT_FAILURE);
}
if (partition < 1 || partition > 8) {
error_report("Invalid partition %d", partition);
exit(EXIT_FAILURE);
}
break;
case 'k':
sockpath = optarg;
if (sockpath[0] != '/') {
error_report("socket path must be absolute");
exit(EXIT_FAILURE);
}
break;
case 'd':
disconnect = true;
break;
case 'c':
device = optarg;
break;
case 'e':
shared = strtol(optarg, &end, 0);
if (*end) {
error_report("Invalid shared device number '%s'", optarg);
exit(EXIT_FAILURE);
}
if (shared < 1) {
error_report("Shared device number must be greater than 0");
exit(EXIT_FAILURE);
}
break;
case 'f':
fmt = optarg;
break;
case 't':
persistent = 1;
break;
case 'x':
export_name = optarg;
break;
case 'D':
export_description = optarg;
break;
case 'v':
verbose = 1;
break;
case 'V':
version(argv[0]);
exit(0);
break;
case 'h':
usage(argv[0]);
exit(0);
break;
case '?':
error_report("Try `%s --help' for more information.", argv[0]);
exit(EXIT_FAILURE);
case QEMU_NBD_OPT_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
exit(EXIT_FAILURE);
}
} break;
case QEMU_NBD_OPT_TLSCREDS:
tlscredsid = optarg;
break;
case QEMU_NBD_OPT_IMAGE_OPTS:
imageOpts = true;
break;
case 'T':
g_free(trace_file);
trace_file = trace_opt_parse(optarg);
break;
case QEMU_NBD_OPT_FORK:
fork_process = true;
break;
}
}
if ((argc - optind) != 1) {
error_report("Invalid number of arguments");
error_printf("Try `%s --help' for more information.\n", argv[0]);
exit(EXIT_FAILURE);
}
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
exit(EXIT_FAILURE);
}
if (!trace_init_backends()) {
exit(1);
}
trace_init_file(trace_file);
qemu_set_log(LOG_TRACE);
socket_activation = check_socket_activation();
if (socket_activation == 0) {
setup_address_and_port(&bindto, &port);
} else {
/* Using socket activation - check user didn't use -p etc. */
const char *err_msg = socket_activation_validate_opts(device, sockpath,
bindto, port);
if (err_msg != NULL) {
error_report("%s", err_msg);
exit(EXIT_FAILURE);
}
/* qemu-nbd can only listen on a single socket. */
if (socket_activation > 1) {
error_report("qemu-nbd does not support socket activation with %s > 1",
"LISTEN_FDS");
exit(EXIT_FAILURE);
}
}
if (tlscredsid) {
if (sockpath) {
error_report("TLS is only supported with IPv4/IPv6");
exit(EXIT_FAILURE);
}
if (device) {
error_report("TLS is not supported with a host device");
exit(EXIT_FAILURE);
}
if (!export_name) {
/* Set the default NBD protocol export name, since
* we *must* use new style protocol for TLS */
export_name = "";
}
tlscreds = nbd_get_tls_creds(tlscredsid, &local_err);
if (local_err) {
error_report("Failed to get TLS creds %s",
error_get_pretty(local_err));
exit(EXIT_FAILURE);
}
}
if (disconnect) {
int nbdfd = open(argv[optind], O_RDWR);
if (nbdfd < 0) {
error_report("Cannot open %s: %s", argv[optind],
strerror(errno));
exit(EXIT_FAILURE);
}
nbd_disconnect(nbdfd);
close(nbdfd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
if ((device && !verbose) || fork_process) {
int stderr_fd[2];
pid_t pid;
int ret;
if (qemu_pipe(stderr_fd) < 0) {
error_report("Error setting up communication pipe: %s",
strerror(errno));
exit(EXIT_FAILURE);
}
/* Now daemonize, but keep a communication channel open to
* print errors and exit with the proper status code.
*/
pid = fork();
if (pid < 0) {
error_report("Failed to fork: %s", strerror(errno));
exit(EXIT_FAILURE);
} else if (pid == 0) {
close(stderr_fd[0]);
ret = qemu_daemon(1, 0);
/* Temporarily redirect stderr to the parent's pipe... */
old_stderr = dup(STDERR_FILENO);
dup2(stderr_fd[1], STDERR_FILENO);
if (ret < 0) {
error_report("Failed to daemonize: %s", strerror(errno));
exit(EXIT_FAILURE);
}
/* ... close the descriptor we inherited and go on. */
close(stderr_fd[1]);
} else {
bool errors = false;
char *buf;
/* In the parent. Print error messages from the child until
* it closes the pipe.
*/
close(stderr_fd[1]);
buf = g_malloc(1024);
while ((ret = read(stderr_fd[0], buf, 1024)) > 0) {
errors = true;
ret = qemu_write_full(STDERR_FILENO, buf, ret);
if (ret < 0) {
exit(EXIT_FAILURE);
}
}
if (ret < 0) {
error_report("Cannot read from daemon: %s",
strerror(errno));
exit(EXIT_FAILURE);
}
/* Usually the daemon should not print any message.
* Exit with zero status in that case.
*/
exit(errors);
}
}
if (device != NULL && sockpath == NULL) {
sockpath = g_malloc(128);
snprintf(sockpath, 128, SOCKET_PATH, basename(device));
}
if (socket_activation == 0) {
server_ioc = qio_channel_socket_new();
saddr = nbd_build_socket_address(sockpath, bindto, port);
if (qio_channel_socket_listen_sync(server_ioc, saddr, &local_err) < 0) {
object_unref(OBJECT(server_ioc));
error_report_err(local_err);
return 1;
}
} else {
/* See comment in check_socket_activation above. */
assert(socket_activation == 1);
server_ioc = qio_channel_socket_new_fd(FIRST_SOCKET_ACTIVATION_FD,
&local_err);
if (server_ioc == NULL) {
error_report("Failed to use socket activation: %s",
error_get_pretty(local_err));
exit(EXIT_FAILURE);
}
}
if (qemu_init_main_loop(&local_err)) {
error_report_err(local_err);
exit(EXIT_FAILURE);
}
bdrv_init();
atexit(bdrv_close_all);
srcpath = argv[optind];
if (imageOpts) {
QemuOpts *opts;
if (fmt) {
error_report("--image-opts and -f are mutually exclusive");
exit(EXIT_FAILURE);
}
opts = qemu_opts_parse_noisily(&file_opts, srcpath, true);
if (!opts) {
qemu_opts_reset(&file_opts);
exit(EXIT_FAILURE);
}
options = qemu_opts_to_qdict(opts, NULL);
qemu_opts_reset(&file_opts);
blk = blk_new_open(NULL, NULL, options, flags, &local_err);
} else {
if (fmt) {
options = qdict_new();
qdict_put_str(options, "driver", fmt);
}
blk = blk_new_open(srcpath, NULL, options, flags, &local_err);
}
if (!blk) {
error_reportf_err(local_err, "Failed to blk_new_open '%s': ",
argv[optind]);
exit(EXIT_FAILURE);
}
bs = blk_bs(blk);
blk_set_enable_write_cache(blk, !writethrough);
if (sn_opts) {
ret = bdrv_snapshot_load_tmp(bs,
qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
&local_err);
} else if (sn_id_or_name) {
ret = bdrv_snapshot_load_tmp_by_id_or_name(bs, sn_id_or_name,
&local_err);
}
if (ret < 0) {
error_reportf_err(local_err, "Failed to load snapshot: ");
exit(EXIT_FAILURE);
}
bs->detect_zeroes = detect_zeroes;
fd_size = blk_getlength(blk);
if (fd_size < 0) {
error_report("Failed to determine the image length: %s",
strerror(-fd_size));
exit(EXIT_FAILURE);
}
if (dev_offset >= fd_size) {
error_report("Offset (%lld) has to be smaller than the image size "
"(%lld)",
(long long int)dev_offset, (long long int)fd_size);
exit(EXIT_FAILURE);
}
fd_size -= dev_offset;
if (partition != -1) {
ret = find_partition(blk, partition, &dev_offset, &fd_size);
if (ret < 0) {
error_report("Could not find partition %d: %s", partition,
strerror(-ret));
exit(EXIT_FAILURE);
}
}
exp = nbd_export_new(bs, dev_offset, fd_size, nbdflags, nbd_export_closed,
writethrough, NULL, &local_err);
if (!exp) {
error_report_err(local_err);
exit(EXIT_FAILURE);
}
if (export_name) {
nbd_export_set_name(exp, export_name);
nbd_export_set_description(exp, export_description);
newproto = true;
} else if (export_description) {
error_report("Export description requires an export name");
exit(EXIT_FAILURE);
}
if (device) {
int ret;
ret = pthread_create(&client_thread, NULL, nbd_client_thread, device);
if (ret != 0) {
error_report("Failed to create client thread: %s", strerror(ret));
exit(EXIT_FAILURE);
}
} else {
/* Shut up GCC warnings. */
memset(&client_thread, 0, sizeof(client_thread));
}
nbd_update_server_watch();
/* now when the initialization is (almost) complete, chdir("/")
* to free any busy filesystems */
if (chdir("/") < 0) {
error_report("Could not chdir to root directory: %s",
strerror(errno));
exit(EXIT_FAILURE);
}
if (fork_process) {
dup2(old_stderr, STDERR_FILENO);
close(old_stderr);
}
state = RUNNING;
do {
main_loop_wait(false);
if (state == TERMINATE) {
state = TERMINATING;
nbd_export_close(exp);
nbd_export_put(exp);
exp = NULL;
}
} while (state != TERMINATED);
blk_unref(blk);
if (sockpath) {
unlink(sockpath);
}
qemu_opts_del(sn_opts);
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
