int qcow2_snapshot_load_tmp(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
int i, snapshot_index;
BDRVQcow2State *s = bs->opaque;
QCowSnapshot *sn;
uint64_t *new_l1_table;
int new_l1_bytes;
int ret;
assert(bs->read_only);
/* Search the snapshot */
snapshot_index = find_snapshot_by_id_and_name(bs, snapshot_id, name);
if (snapshot_index < 0) {
error_setg(errp,
"Can't find snapshot");
return -ENOENT;
}
sn = &s->snapshots[snapshot_index];
/* Allocate and read in the snapshot's L1 table */
if (sn->l1_size > QCOW_MAX_L1_SIZE / sizeof(uint64_t)) {
error_setg(errp, "Snapshot L1 table too large");
return -EFBIG;
}
new_l1_bytes = sn->l1_size * sizeof(uint64_t);
new_l1_table = qemu_try_blockalign(bs->file->bs,
align_offset(new_l1_bytes, 512));
if (new_l1_table == NULL) {
return -ENOMEM;
}
ret = bdrv_pread(bs->file->bs, sn->l1_table_offset,
new_l1_table, new_l1_bytes);
if (ret < 0) {
error_setg(errp, "Failed to read l1 table for snapshot");
qemu_vfree(new_l1_table);
return ret;
}
/* Switch the L1 table */
qemu_vfree(s->l1_table);
s->l1_size = sn->l1_size;
s->l1_table_offset = sn->l1_table_offset;
s->l1_table = new_l1_table;
for(i = 0;i < s->l1_size; i++) {
be64_to_cpus(&s->l1_table[i]);
}
return 0;
}
static void vhdx_close(BlockDriverState *bs)
{
BDRVVHDXState *s = bs->opaque;
qemu_vfree(s->headers[0]);
qemu_vfree(s->headers[1]);
qemu_vfree(s->bat);
qemu_vfree(s->parent_entries);
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
static void dmg_close(BlockDriverState *bs)
{
BDRVDMGState *s = bs->opaque;
g_free(s->types);
g_free(s->offsets);
g_free(s->lengths);
g_free(s->sectors);
g_free(s->sectorcounts);
qemu_vfree(s->compressed_chunk);
qemu_vfree(s->uncompressed_chunk);
inflateEnd(&s->zstream);
}
static void complete_request(struct iocb *iocb, ssize_t ret, void *opaque)
{
VirtIOBlockDataPlane *s = opaque;
VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
struct virtio_blk_inhdr hdr;
int len;
if (likely(ret >= 0)) {
hdr.status = VIRTIO_BLK_S_OK;
len = ret;
} else {
hdr.status = VIRTIO_BLK_S_IOERR;
len = 0;
}
trace_virtio_blk_data_plane_complete_request(s, req->head, ret);
if (req->read_qiov) {
assert(req->bounce_iov);
qemu_iovec_from_buf(req->read_qiov, 0, req->bounce_iov->iov_base, len);
qemu_iovec_destroy(req->read_qiov);
g_slice_free(QEMUIOVector, req->read_qiov);
}
if (req->bounce_iov) {
qemu_vfree(req->bounce_iov->iov_base);
g_slice_free(struct iovec, req->bounce_iov);
}
static void qemu_io_free(void *p)
{
if (misalign) {
p -= MISALIGN_OFFSET;
}
qemu_vfree(p);
}
/*
* Completes an AIO request (calls the callback and frees the ACB).
*/
static void win32_aio_process_completion(QEMUWin32AIOState *s,
QEMUWin32AIOCB *waiocb, DWORD count)
{
int ret;
s->count--;
if (waiocb->ov.Internal != 0) {
ret = -EIO;
} else {
ret = 0;
if (count < waiocb->nbytes) {
/* Short reads mean EOF, pad with zeros. */
if (waiocb->is_read) {
qemu_iovec_memset(waiocb->qiov, count, 0,
waiocb->qiov->size - count);
} else {
ret = -EINVAL;
}
}
}
if (!waiocb->is_linear) {
if (ret == 0 && waiocb->is_read) {
QEMUIOVector *qiov = waiocb->qiov;
iov_from_buf(qiov->iov, qiov->niov, 0, waiocb->buf, qiov->size);
}
qemu_vfree(waiocb->buf);
}
waiocb->common.cb(waiocb->common.opaque, ret);
qemu_aio_release(waiocb);
}
static void qed_write_table_cb(void *opaque, int ret)
{
QEDWriteTableCB *write_table_cb = opaque;
trace_qed_write_table_cb(write_table_cb->s,
write_table_cb->orig_table,
write_table_cb->flush,
ret);
if (ret) {
goto out;
}
if (write_table_cb->flush) {
/* We still need to flush first */
write_table_cb->flush = false;
bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb,
write_table_cb);
return;
}
out:
qemu_vfree(write_table_cb->table);
gencb_complete(&write_table_cb->gencb, ret);
return;
}
static void qed_write_header_cb(void *opaque, int ret)
{
QEDWriteHeaderCB *write_header_cb = opaque;
qemu_vfree(write_header_cb->buf);
gencb_complete(write_header_cb, ret);
}
static int coroutine_fn
raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
QEMUIOVector *qiov, int flags)
{
void *buf = NULL;
BlockDriver *drv;
QEMUIOVector local_qiov;
int ret;
if (bs->probed && sector_num == 0) {
/* As long as these conditions are true, we can't get partial writes to
* the probe buffer and can just directly check the request. */
QEMU_BUILD_BUG_ON(BLOCK_PROBE_BUF_SIZE != 512);
QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != 512);
if (nb_sectors == 0) {
/* qemu_iovec_to_buf() would fail, but we want to return success
* instead of -EINVAL in this case. */
return 0;
}
buf = qemu_try_blockalign(bs->file->bs, 512);
if (!buf) {
ret = -ENOMEM;
goto fail;
}
ret = qemu_iovec_to_buf(qiov, 0, buf, 512);
if (ret != 512) {
ret = -EINVAL;
goto fail;
}
drv = bdrv_probe_all(buf, 512, NULL);
if (drv != bs->drv) {
ret = -EPERM;
goto fail;
}
/* Use the checked buffer, a malicious guest might be overwriting its
* original buffer in the background. */
qemu_iovec_init(&local_qiov, qiov->niov + 1);
qemu_iovec_add(&local_qiov, buf, 512);
qemu_iovec_concat(&local_qiov, qiov, 512, qiov->size - 512);
qiov = &local_qiov;
}
BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
ret = bdrv_co_do_pwritev(bs->file->bs, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE, qiov, flags);
fail:
if (qiov == &local_qiov) {
qemu_iovec_destroy(&local_qiov);
}
qemu_vfree(buf);
return ret;
}
static void raw_close(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
if (s->fd >= 0) {
close(s->fd);
s->fd = -1;
if (s->aligned_buf != NULL)
qemu_vfree(s->aligned_buf);
}
}
static void vpc_close(BlockDriverState *bs)
{
BDRVVPCState *s = bs->opaque;
qemu_vfree(s->pagetable);
#ifdef CACHE
g_free(s->pageentry_u8);
#endif
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
void nbd_export_close(NBDExport *exp)
{
while (!QSIMPLEQ_EMPTY(&exp->requests)) {
NBDRequest *first = QSIMPLEQ_FIRST(&exp->requests);
QSIMPLEQ_REMOVE_HEAD(&exp->requests, entry);
qemu_vfree(first->data);
g_free(first);
}
bdrv_close(exp->bs);
g_free(exp);
}
/* Reads the log header, and subsequent descriptors (if any). This
* will allocate all the space for buffer, which must be NULL when
* passed into this function. Each descriptor will also be validated,
* and error returned if any are invalid. */
static int vhdx_log_read_desc(BlockDriverState *bs, BDRVVHDXState *s,
VHDXLogEntries *log, VHDXLogDescEntries **buffer)
{
int ret = 0;
uint32_t desc_sectors;
uint32_t sectors_read;
VHDXLogEntryHeader hdr;
VHDXLogDescEntries *desc_entries = NULL;
int i;
assert(*buffer == NULL);
ret = vhdx_log_peek_hdr(bs, log, &hdr);
if (ret < 0) {
goto exit;
}
vhdx_log_entry_hdr_le_import(&hdr);
if (vhdx_log_hdr_is_valid(log, &hdr, s) == false) {
ret = -EINVAL;
goto exit;
}
desc_sectors = vhdx_compute_desc_sectors(hdr.descriptor_count);
desc_entries = qemu_blockalign(bs, desc_sectors * VHDX_LOG_SECTOR_SIZE);
ret = vhdx_log_read_sectors(bs, log, §ors_read, desc_entries,
desc_sectors, false);
if (ret < 0) {
goto free_and_exit;
}
if (sectors_read != desc_sectors) {
ret = -EINVAL;
goto free_and_exit;
}
/* put in proper endianness, and validate each desc */
for (i = 0; i < hdr.descriptor_count; i++) {
vhdx_log_desc_le_import(&desc_entries->desc[i]);
if (vhdx_log_desc_is_valid(&desc_entries->desc[i], &hdr) == false) {
ret = -EINVAL;
goto free_and_exit;
}
}
*buffer = desc_entries;
goto exit;
free_and_exit:
qemu_vfree(desc_entries);
exit:
return ret;
}
static void rbd_aio_bh_cb(void *opaque)
{
RBDAIOCB *acb = opaque;
if (acb->cmd == RBD_AIO_READ) {
qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
}
qemu_vfree(acb->bounce);
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
qemu_bh_delete(acb->bh);
acb->bh = NULL;
qemu_aio_release(acb);
}
int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c)
{
int i;
for (i = 0; i < c->size; i++) {
assert(c->entries[i].ref == 0);
qemu_vfree(c->entries[i].table);
}
qemu_free(c->entries);
qemu_free(c);
return 0;
}
static void blkverify_aio_bh(void *opaque)
{
BlkverifyAIOCB *acb = opaque;
qemu_bh_delete(acb->bh);
if (acb->buf) {
qemu_iovec_destroy(&acb->raw_qiov);
qemu_vfree(acb->buf);
}
acb->common.cb(acb->common.opaque, acb->ret);
if (acb->finished) {
*acb->finished = true;
}
qemu_aio_release(acb);
}
static void bdrv_qed_close(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
/* Ensure writes reach stable storage */
bdrv_flush(bs->file);
/* Clean shutdown, no check required on next open */
if (s->header.features & QED_F_NEED_CHECK) {
s->header.features &= ~QED_F_NEED_CHECK;
qed_write_header_sync(s);
}
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
}
/*
* This aio completion is being called from rbd_finish_bh() and runs in qemu
* BH context.
*/
static void qemu_rbd_complete_aio(RADOSCB *rcb)
{
RBDAIOCB *acb = rcb->acb;
int64_t r;
r = rcb->ret;
if (acb->cmd != RBD_AIO_READ) {
if (r < 0) {
acb->ret = r;
acb->error = 1;
} else if (!acb->error) {
acb->ret = rcb->size;
}
} else {
if (r < 0) {
qemu_rbd_memset(rcb, 0);
acb->ret = r;
acb->error = 1;
} else if (r < rcb->size) {
qemu_rbd_memset(rcb, r);
if (!acb->error) {
acb->ret = rcb->size;
}
} else if (!acb->error) {
acb->ret = r;
}
}
g_free(rcb);
if (!LIBRBD_USE_IOVEC) {
if (acb->cmd == RBD_AIO_READ) {
qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
}
qemu_vfree(acb->bounce);
}
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
qemu_aio_unref(acb);
}
/*
* This aio completion is being called from rbd_finish_bh() and runs in qemu
* BH context.
*/
static void qemu_rbd_complete_aio(RADOSCB *rcb)
{
RBDAIOCB *acb = rcb->acb;
int64_t r;
r = rcb->ret;
if (acb->cmd != RBD_AIO_READ) {
if (r < 0) {
acb->ret = r;
acb->error = 1;
} else if (!acb->error) {
acb->ret = rcb->size;
}
} else {
if (r < 0) {
memset(rcb->buf, 0, rcb->size);
acb->ret = r;
acb->error = 1;
} else if (r < rcb->size) {
memset(rcb->buf + r, 0, rcb->size - r);
if (!acb->error) {
acb->ret = rcb->size;
}
} else if (!acb->error) {
acb->ret = r;
}
}
g_free(rcb);
if (acb->cmd == RBD_AIO_READ) {
qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
}
qemu_vfree(acb->bounce);
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
acb->status = 0;
if (!acb->cancelled) {
qemu_aio_release(acb);
}
}
Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
{
BDRVQcowState *s = bs->opaque;
Qcow2Cache *c;
c = g_new0(Qcow2Cache, 1);
c->size = num_tables;
c->entries = g_try_new0(Qcow2CachedTable, num_tables);
c->table_array = qemu_try_blockalign(bs->file,
(size_t) num_tables * s->cluster_size);
if (!c->entries || !c->table_array) {
qemu_vfree(c->table_array);
g_free(c->entries);
g_free(c);
c = NULL;
}
return c;
}
/*
* This aio completion is being called from qemu_rbd_aio_event_reader()
* and runs in qemu context. It schedules a bh, but just in case the aio
* was not cancelled before.
*/
static void qemu_rbd_complete_aio(RADOSCB *rcb)
{
RBDAIOCB *acb = rcb->acb;
int64_t r;
if (acb->cancelled) {
qemu_vfree(acb->bounce);
qemu_aio_release(acb);
goto done;
}
r = rcb->ret;
if (acb->cmd == RBD_AIO_WRITE ||
acb->cmd == RBD_AIO_DISCARD) {
if (r < 0) {
acb->ret = r;
acb->error = 1;
} else if (!acb->error) {
acb->ret = rcb->size;
}
} else {
if (r < 0) {
memset(rcb->buf, 0, rcb->size);
acb->ret = r;
acb->error = 1;
} else if (r < rcb->size) {
memset(rcb->buf + r, 0, rcb->size - r);
if (!acb->error) {
acb->ret = rcb->size;
}
} else if (!acb->error) {
acb->ret = r;
}
}
/* Note that acb->bh can be NULL in case where the aio was cancelled */
acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
qemu_bh_schedule(acb->bh);
done:
g_free(rcb);
}
void xen_block_dataplane_destroy(XenBlockDataPlane *dataplane)
{
XenBlockRequest *request;
if (!dataplane) {
return;
}
while (!QLIST_EMPTY(&dataplane->freelist)) {
request = QLIST_FIRST(&dataplane->freelist);
QLIST_REMOVE(request, list);
qemu_iovec_destroy(&request->v);
qemu_vfree(request->buf);
g_free(request);
}
qemu_bh_delete(dataplane->bh);
if (dataplane->iothread) {
object_unref(OBJECT(dataplane->iothread));
}
g_free(dataplane);
}
static void compare_full_images_cb (void *opaque, int ret)
{
CompareFullCB *cf = opaque;
if (ret) {
/* Failed. Retry the operation. */
bdrv_aio_readv (bs, cf->sector_num, &cf->qiov, cf->nb_sectors,
compare_full_images_cb, cf);
return;
}
truth_io (cf->truth_buf, cf->sector_num, cf->nb_sectors, TRUE);
verify (cf->truth_buf, cf->iov.iov_base, cf->sector_num, cf->nb_sectors);
cf->sector_num += cf->nb_sectors;
if (cf->sector_num >= total_sectors) {
/* Finished. */
free (cf->truth_buf);
qemu_vfree (cf->iov.iov_base);
g_free(cf);
return;
}
/* Read more data to compare. */
if (cf->sector_num + cf->max_nb_sectors > total_sectors) {
cf->nb_sectors = total_sectors - cf->sector_num;
} else {
cf->nb_sectors = cf->max_nb_sectors;
}
cf->iov.iov_len = cf->nb_sectors * 512;
qemu_iovec_init_external (&cf->qiov, &cf->iov, 1);
if (!bdrv_aio_readv (bs, cf->sector_num, &cf->qiov,
cf->nb_sectors, compare_full_images_cb, cf)) {
die ("bdrv_aio_readv\n");
}
}
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
MirrorExitData *data;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, sectors_per_chunk, length;
uint64_t last_pause_ns;
BlockDriverInfo bdi;
char backing_filename[2]; /* we only need 2 characters because we are only
checking for a NULL string */
int ret = 0;
int n;
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;
} else 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(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->bdev_length / BDRV_SECTOR_SIZE;
s->buf = qemu_try_blockalign(bs, s->buf_size);
if (s->buf == NULL) {
ret = -ENOMEM;
goto immediate_exit;
}
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_bitmap(s->dirty_bitmap, sector_num, n);
sector_num = next;
} else {
sector_num += n;
}
}
}
bdrv_dirty_iter_init(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(s->dirty_bitmap);
/* s->common.offset contains the number of bytes already processed so
* far, cnt is the number of dirty sectors remaining and
* s->sectors_in_flight is the number of sectors currently being
* processed; together those are the current total operation length */
s->common.len = s->common.offset +
(cnt + s->sectors_in_flight) * BDRV_SECTOR_SIZE;
/* 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 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);
}
}
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.
*/
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(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(bs);
cnt = bdrv_get_dirty_count(s->dirty_bitmap);
}
ret = 0;
trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
if (!s->synced) {
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);
data = g_malloc(sizeof(*data));
data->ret = ret;
block_job_defer_to_main_loop(&s->common, mirror_exit, data);
}
static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVQEDState *s = bs->opaque;
QEDHeader le_header;
int64_t file_size;
int ret;
s->bs = bs;
QSIMPLEQ_INIT(&s->allocating_write_reqs);
ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header));
if (ret < 0) {
return ret;
}
qed_header_le_to_cpu(&le_header, &s->header);
if (s->header.magic != QED_MAGIC) {
error_setg(errp, "Image not in QED format");
return -EINVAL;
}
if (s->header.features & ~QED_FEATURE_MASK) {
/* image uses unsupported feature bits */
char buf[64];
snprintf(buf, sizeof(buf), "%" PRIx64,
s->header.features & ~QED_FEATURE_MASK);
error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
bs->device_name, "QED", buf);
return -ENOTSUP;
}
if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
return -EINVAL;
}
/* Round down file size to the last cluster */
file_size = bdrv_getlength(bs->file);
if (file_size < 0) {
return file_size;
}
s->file_size = qed_start_of_cluster(s, file_size);
if (!qed_is_table_size_valid(s->header.table_size)) {
return -EINVAL;
}
if (!qed_is_image_size_valid(s->header.image_size,
s->header.cluster_size,
s->header.table_size)) {
return -EINVAL;
}
if (!qed_check_table_offset(s, s->header.l1_table_offset)) {
return -EINVAL;
}
s->table_nelems = (s->header.cluster_size * s->header.table_size) /
sizeof(uint64_t);
s->l2_shift = ffs(s->header.cluster_size) - 1;
s->l2_mask = s->table_nelems - 1;
s->l1_shift = s->l2_shift + ffs(s->table_nelems) - 1;
if ((s->header.features & QED_F_BACKING_FILE)) {
if ((uint64_t)s->header.backing_filename_offset +
s->header.backing_filename_size >
s->header.cluster_size * s->header.header_size) {
return -EINVAL;
}
ret = qed_read_string(bs->file, s->header.backing_filename_offset,
s->header.backing_filename_size, bs->backing_file,
sizeof(bs->backing_file));
if (ret < 0) {
return ret;
}
if (s->header.features & QED_F_BACKING_FORMAT_NO_PROBE) {
pstrcpy(bs->backing_format, sizeof(bs->backing_format), "raw");
}
}
/* Reset unknown autoclear feature bits. This is a backwards
* compatibility mechanism that allows images to be opened by older
* programs, which "knock out" unknown feature bits. When an image is
* opened by a newer program again it can detect that the autoclear
* feature is no longer valid.
*/
if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
!bdrv_is_read_only(bs->file) && !(flags & BDRV_O_INCOMING)) {
s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;
ret = qed_write_header_sync(s);
if (ret) {
return ret;
}
/* From here on only known autoclear feature bits are valid */
bdrv_flush(bs->file);
}
s->l1_table = qed_alloc_table(s);
qed_init_l2_cache(&s->l2_cache);
ret = qed_read_l1_table_sync(s);
if (ret) {
goto out;
}
/* If image was not closed cleanly, check consistency */
if (!(flags & BDRV_O_CHECK) && (s->header.features & QED_F_NEED_CHECK)) {
/* Read-only images cannot be fixed. There is no risk of corruption
* since write operations are not possible. Therefore, allow
* potentially inconsistent images to be opened read-only. This can
* aid data recovery from an otherwise inconsistent image.
*/
if (!bdrv_is_read_only(bs->file) &&
!(flags & BDRV_O_INCOMING)) {
BdrvCheckResult result = {0};
ret = qed_check(s, &result, true);
if (ret) {
goto out;
}
}
}
bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs));
out:
if (ret) {
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
}
return ret;
}
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);
}
int main(int argc, char **argv)
{
BlockDriverState *bs;
off_t dev_offset = 0;
off_t offset = 0;
bool readonly = false;
bool disconnect = false;
const char *bindto = "0.0.0.0";
int port = NBD_DEFAULT_PORT;
struct sockaddr_in addr;
socklen_t addr_len = sizeof(addr);
off_t fd_size;
char *device = NULL;
char *socket = NULL;
char sockpath[128];
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:t";
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' },
{ "nocache", 0, NULL, 'n' },
{ "shared", 1, NULL, 'e' },
{ "persistent", 0, NULL, 't' },
{ "verbose", 0, NULL, 'v' },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
int li;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret;
int shared = 1;
uint8_t *data;
fd_set fds;
int *sharing_fds;
int fd;
int i;
int nb_fds = 0;
int max_fd;
int persistent = 0;
uint32_t nbdflags;
while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) {
switch (ch) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
flags |= BDRV_O_NOCACHE;
break;
case 'b':
bindto = optarg;
break;
case 'p':
li = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid port `%s'", optarg);
}
if (li < 1 || li > 65535) {
errx(EXIT_FAILURE, "Port out of range `%s'", optarg);
}
port = (uint16_t)li;
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 'r':
readonly = true;
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':
socket = optarg;
if (socket[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 '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 == -1)
err(EXIT_FAILURE, "Cannot open %s", argv[optind]);
nbd_disconnect(fd);
close(fd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
bdrv_init();
bs = bdrv_new("hda");
if (bs == NULL)
return 1;
if ((ret = bdrv_open(bs, argv[optind], flags, NULL)) < 0) {
errno = -ret;
err(EXIT_FAILURE, "Failed to bdrv_open '%s'", argv[optind]);
}
fd_size = bs->total_sectors * 512;
if (partition != -1 &&
find_partition(bs, partition, &dev_offset, &fd_size))
err(EXIT_FAILURE, "Could not find partition %d", partition);
if (device) {
pid_t pid;
int sock;
/* want to fail before daemonizing */
if (access(device, R_OK|W_OK) == -1) {
err(EXIT_FAILURE, "Could not access '%s'", device);
}
if (!verbose) {
/* detach client and server */
if (daemon(0, 0) == -1) {
err(EXIT_FAILURE, "Failed to daemonize");
}
}
if (socket == NULL) {
snprintf(sockpath, sizeof(sockpath), SOCKET_PATH,
basename(device));
socket = sockpath;
}
pid = fork();
if (pid < 0)
return 1;
if (pid != 0) {
off_t size;
size_t blocksize;
ret = 0;
bdrv_close(bs);
do {
sock = unix_socket_outgoing(socket);
if (sock == -1) {
if (errno != ENOENT && errno != ECONNREFUSED) {
ret = 1;
goto out;
}
sleep(1); /* wait children */
}
} while (sock == -1);
fd = open(device, O_RDWR);
if (fd == -1) {
ret = 1;
goto out;
}
ret = nbd_receive_negotiate(sock, NULL, &nbdflags,
&size, &blocksize);
if (ret == -1) {
ret = 1;
goto out;
}
ret = nbd_init(fd, sock, size, blocksize);
if (ret == -1) {
ret = 1;
goto out;
}
printf("NBD device %s is now connected to file %s\n",
device, argv[optind]);
/* update partition table */
show_parts(device);
ret = nbd_client(fd);
if (ret) {
ret = 1;
}
close(fd);
out:
kill(pid, SIGTERM);
unlink(socket);
return ret;
}
/* children */
}
sharing_fds = qemu_malloc((shared + 1) * sizeof(int));
if (socket) {
sharing_fds[0] = unix_socket_incoming(socket);
} else {
sharing_fds[0] = tcp_socket_incoming(bindto, port);
}
if (sharing_fds[0] == -1)
return 1;
max_fd = sharing_fds[0];
nb_fds++;
data = qemu_blockalign(bs, NBD_BUFFER_SIZE);
if (data == NULL)
errx(EXIT_FAILURE, "Cannot allocate data buffer");
do {
FD_ZERO(&fds);
for (i = 0; i < nb_fds; i++)
FD_SET(sharing_fds[i], &fds);
ret = select(max_fd + 1, &fds, NULL, NULL, NULL);
if (ret == -1)
break;
if (FD_ISSET(sharing_fds[0], &fds))
ret--;
for (i = 1; i < nb_fds && ret; i++) {
if (FD_ISSET(sharing_fds[i], &fds)) {
if (nbd_trip(bs, sharing_fds[i], fd_size, dev_offset,
&offset, readonly, data, NBD_BUFFER_SIZE) != 0) {
close(sharing_fds[i]);
nb_fds--;
sharing_fds[i] = sharing_fds[nb_fds];
i--;
}
ret--;
}
}
/* new connection ? */
if (FD_ISSET(sharing_fds[0], &fds)) {
if (nb_fds < shared + 1) {
sharing_fds[nb_fds] = accept(sharing_fds[0],
(struct sockaddr *)&addr,
&addr_len);
if (sharing_fds[nb_fds] != -1 &&
nbd_negotiate(sharing_fds[nb_fds], fd_size) != -1) {
if (sharing_fds[nb_fds] > max_fd)
max_fd = sharing_fds[nb_fds];
nb_fds++;
}
}
}
} while (persistent || nb_fds > 1);
qemu_vfree(data);
close(sharing_fds[0]);
bdrv_close(bs);
qemu_free(sharing_fds);
if (socket)
unlink(socket);
return 0;
}
static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVDMGState *s = bs->opaque;
DmgHeaderState ds;
uint64_t rsrc_fork_offset, rsrc_fork_length;
uint64_t plist_xml_offset, plist_xml_length;
int64_t offset;
int ret;
block_module_load_one("dmg-bz2");
bs->read_only = true;
s->n_chunks = 0;
s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
/* used by dmg_read_mish_block to keep track of the current I/O position */
ds.data_fork_offset = 0;
ds.max_compressed_size = 1;
ds.max_sectors_per_chunk = 1;
/* locate the UDIF trailer */
offset = dmg_find_koly_offset(bs->file, errp);
if (offset < 0) {
ret = offset;
goto fail;
}
/* offset of data fork (DataForkOffset) */
ret = read_uint64(bs, offset + 0x18, &ds.data_fork_offset);
if (ret < 0) {
goto fail;
} else if (ds.data_fork_offset > offset) {
ret = -EINVAL;
goto fail;
}
/* offset of resource fork (RsrcForkOffset) */
ret = read_uint64(bs, offset + 0x28, &rsrc_fork_offset);
if (ret < 0) {
goto fail;
}
ret = read_uint64(bs, offset + 0x30, &rsrc_fork_length);
if (ret < 0) {
goto fail;
}
if (rsrc_fork_offset >= offset ||
rsrc_fork_length > offset - rsrc_fork_offset) {
ret = -EINVAL;
goto fail;
}
/* offset of property list (XMLOffset) */
ret = read_uint64(bs, offset + 0xd8, &plist_xml_offset);
if (ret < 0) {
goto fail;
}
ret = read_uint64(bs, offset + 0xe0, &plist_xml_length);
if (ret < 0) {
goto fail;
}
if (plist_xml_offset >= offset ||
plist_xml_length > offset - plist_xml_offset) {
ret = -EINVAL;
goto fail;
}
ret = read_uint64(bs, offset + 0x1ec, (uint64_t *)&bs->total_sectors);
if (ret < 0) {
goto fail;
}
if (bs->total_sectors < 0) {
ret = -EINVAL;
goto fail;
}
if (rsrc_fork_length != 0) {
ret = dmg_read_resource_fork(bs, &ds,
rsrc_fork_offset, rsrc_fork_length);
if (ret < 0) {
goto fail;
}
} else if (plist_xml_length != 0) {
ret = dmg_read_plist_xml(bs, &ds, plist_xml_offset, plist_xml_length);
if (ret < 0) {
goto fail;
}
} else {
ret = -EINVAL;
goto fail;
}
/* initialize zlib engine */
s->compressed_chunk = qemu_try_blockalign(bs->file->bs,
ds.max_compressed_size + 1);
s->uncompressed_chunk = qemu_try_blockalign(bs->file->bs,
512 * ds.max_sectors_per_chunk);
if (s->compressed_chunk == NULL || s->uncompressed_chunk == NULL) {
ret = -ENOMEM;
goto fail;
}
if (inflateInit(&s->zstream) != Z_OK) {
ret = -EINVAL;
goto fail;
}
s->current_chunk = s->n_chunks;
qemu_co_mutex_init(&s->lock);
return 0;
fail:
g_free(s->types);
g_free(s->offsets);
g_free(s->lengths);
g_free(s->sectors);
g_free(s->sectorcounts);
qemu_vfree(s->compressed_chunk);
qemu_vfree(s->uncompressed_chunk);
return ret;
}
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 BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
int64_t off,
QEMUIOVector *qiov,
int64_t size,
BlockCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
{
RBDAIOCB *acb;
RADOSCB *rcb = NULL;
rbd_completion_t c;
int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
acb->cmd = cmd;
acb->qiov = qiov;
assert(!qiov || qiov->size == size);
rcb = g_new(RADOSCB, 1);
if (!LIBRBD_USE_IOVEC) {
if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
acb->bounce = NULL;
} else {
acb->bounce = qemu_try_blockalign(bs, qiov->size);
if (acb->bounce == NULL) {
goto failed;
}
}
if (cmd == RBD_AIO_WRITE) {
qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
rcb->buf = acb->bounce;
}
acb->ret = 0;
acb->error = 0;
acb->s = s;
rcb->acb = acb;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
if (r < 0) {
goto failed;
}
switch (cmd) {
case RBD_AIO_WRITE:
#ifdef LIBRBD_SUPPORTS_IOVEC
r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, off, c);
#else
r = rbd_aio_write(s->image, off, size, rcb->buf, c);
#endif
break;
case RBD_AIO_READ:
#ifdef LIBRBD_SUPPORTS_IOVEC
r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, off, c);
#else
r = rbd_aio_read(s->image, off, size, rcb->buf, c);
#endif
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
break;
case RBD_AIO_FLUSH:
r = rbd_aio_flush_wrapper(s->image, c);
break;
default:
r = -EINVAL;
}
if (r < 0) {
goto failed_completion;
}
return &acb->common;
failed_completion:
rbd_aio_release(c);
failed:
g_free(rcb);
if (!LIBRBD_USE_IOVEC) {
qemu_vfree(acb->bounce);
}
qemu_aio_unref(acb);
return NULL;
}
