/**
* Delete an internal snapshot by @snapshot_id and @name.
* @bs: block device used in the operation
* @snapshot_id: unique snapshot ID, or NULL
* @name: snapshot name, or NULL
* @errp: location to store error
*
* If both @snapshot_id and @name are specified, delete the first one with
* id @snapshot_id and name @name.
* If only @snapshot_id is specified, delete the first one with id
* @snapshot_id.
* If only @name is specified, delete the first one with name @name.
* if none is specified, return -EINVAL.
*
* Returns: 0 on success, -errno on failure. If @bs is not inserted, return
* -ENOMEDIUM. If @snapshot_id and @name are both NULL, return -EINVAL. If @bs
* does not support internal snapshot deletion, return -ENOTSUP. If @bs does
* not support parameter @snapshot_id or @name, or one of them is not correctly
* specified, return -EINVAL. If @bs can't find one matching @id and @name,
* return -ENOENT. If @errp != NULL, it will always be filled with error
* message on failure.
*/
int bdrv_snapshot_delete(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
BlockDriver *drv = bs->drv;
if (!drv) {
error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
return -ENOMEDIUM;
}
if (!snapshot_id && !name) {
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
/* drain all pending i/o before deleting snapshot */
bdrv_drain_all();
if (drv->bdrv_snapshot_delete) {
return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
}
if (bs->file) {
return bdrv_snapshot_delete(bs->file, snapshot_id, name, errp);
}
error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
drv->format_name, bdrv_get_device_name(bs),
"internal snapshot deletion");
return -ENOTSUP;
}
static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
{
BlockStats *s;
s = g_malloc0(sizeof(*s));
if (bdrv_get_device_name(bs)[0]) {
s->has_device = true;
s->device = g_strdup(bdrv_get_device_name(bs));
}
s->stats = g_malloc0(sizeof(*s->stats));
s->stats->rd_bytes = bs->stats.nr_bytes[BLOCK_ACCT_READ];
s->stats->wr_bytes = bs->stats.nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = bs->stats.nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = bs->stats.nr_ops[BLOCK_ACCT_WRITE];
s->stats->wr_highest_offset =
bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];
s->stats->wr_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_WRITE];
s->stats->rd_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_READ];
s->stats->flush_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_FLUSH];
if (bs->file) {
s->has_parent = true;
s->parent = bdrv_query_stats(bs->file);
}
if (bs->backing_hd) {
s->has_backing = true;
s->backing = bdrv_query_stats(bs->backing_hd);
}
return s;
}
/**
* Temporarily load an internal snapshot by @snapshot_id and @name.
* @bs: block device used in the operation
* @snapshot_id: unique snapshot ID, or NULL
* @name: snapshot name, or NULL
* @errp: location to store error
*
* If both @snapshot_id and @name are specified, load the first one with
* id @snapshot_id and name @name.
* If only @snapshot_id is specified, load the first one with id
* @snapshot_id.
* If only @name is specified, load the first one with name @name.
* if none is specified, return -EINVAL.
*
* Returns: 0 on success, -errno on fail. If @bs is not inserted, return
* -ENOMEDIUM. If @bs is not readonly, return -EINVAL. If @bs did not support
* internal snapshot, return -ENOTSUP. If qemu can't find a matching @id and
* @name, return -ENOENT. If @errp != NULL, it will always be filled on
* failure.
*/
int bdrv_snapshot_load_tmp(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
BlockDriver *drv = bs->drv;
if (!drv) {
error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
return -ENOMEDIUM;
}
if (!snapshot_id && !name) {
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
if (!bs->read_only) {
error_setg(errp, "Device is not readonly");
return -EINVAL;
}
if (drv->bdrv_snapshot_load_tmp) {
return drv->bdrv_snapshot_load_tmp(bs, snapshot_id, name, errp);
}
error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
drv->format_name, bdrv_get_device_name(bs),
"temporarily load internal snapshot");
return -ENOTSUP;
}
/**
* Delete an internal snapshot by @snapshot_id and @name.
* @bs: block device used in the operation
* @snapshot_id: unique snapshot ID, or NULL
* @name: snapshot name, or NULL
* @errp: location to store error
*
* If both @snapshot_id and @name are specified, delete the first one with
* id @snapshot_id and name @name.
* If only @snapshot_id is specified, delete the first one with id
* @snapshot_id.
* If only @name is specified, delete the first one with name @name.
* if none is specified, return -EINVAL.
*
* Returns: 0 on success, -errno on failure. If @bs is not inserted, return
* -ENOMEDIUM. If @snapshot_id and @name are both NULL, return -EINVAL. If @bs
* does not support internal snapshot deletion, return -ENOTSUP. If @bs does
* not support parameter @snapshot_id or @name, or one of them is not correctly
* specified, return -EINVAL. If @bs can't find one matching @id and @name,
* return -ENOENT. If @errp != NULL, it will always be filled with error
* message on failure.
*/
int bdrv_snapshot_delete(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
BlockDriver *drv = bs->drv;
if (!drv) {
error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
return -ENOMEDIUM;
}
if (!snapshot_id && !name) {
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
/* drain all pending i/o before deleting snapshot */
bdrv_drain(bs);
if (drv->bdrv_snapshot_delete) {
return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
}
if (bs->file) {
return bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
}
error_setg(errp, "Block format '%s' used by device '%s' "
"does not support internal snapshot deletion",
drv->format_name, bdrv_get_device_name(bs));
return -ENOTSUP;
}
/**
* Temporarily load an internal snapshot by @snapshot_id and @name.
* @bs: block device used in the operation
* @snapshot_id: unique snapshot ID, or NULL
* @name: snapshot name, or NULL
* @errp: location to store error
*
* If both @snapshot_id and @name are specified, load the first one with
* id @snapshot_id and name @name.
* If only @snapshot_id is specified, load the first one with id
* @snapshot_id.
* If only @name is specified, load the first one with name @name.
* if none is specified, return -EINVAL.
*
* Returns: 0 on success, -errno on fail. If @bs is not inserted, return
* -ENOMEDIUM. If @bs is not readonly, return -EINVAL. If @bs did not support
* internal snapshot, return -ENOTSUP. If qemu can't find a matching @id and
* @name, return -ENOENT. If @errp != NULL, it will always be filled on
* failure.
*/
int bdrv_snapshot_load_tmp(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
BlockDriver *drv = bs->drv;
if (!drv) {
error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
return -ENOMEDIUM;
}
if (!snapshot_id && !name) {
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
if (!bs->read_only) {
error_setg(errp, "Device is not readonly");
return -EINVAL;
}
if (drv->bdrv_snapshot_load_tmp) {
return drv->bdrv_snapshot_load_tmp(bs, snapshot_id, name, errp);
}
error_setg(errp, "Block format '%s' used by device '%s' "
"does not support temporarily loading internal snapshots",
drv->format_name, bdrv_get_device_name(bs));
return -ENOTSUP;
}
void *block_job_create(const BlockJobType *job_type, BlockDriverState *bs,
int64_t speed, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
BlockJob *job;
if (bs->job || bdrv_in_use(bs)) {
error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
return NULL;
}
bdrv_set_in_use(bs, 1);
job = g_malloc0(job_type->instance_size);
job->job_type = job_type;
job->bs = bs;
job->cb = cb;
job->opaque = opaque;
job->busy = true;
bs->job = job;
/* Only set speed when necessary to avoid NotSupported error */
if (speed != 0) {
Error *local_err = NULL;
block_job_set_speed(job, speed, &local_err);
if (error_is_set(&local_err)) {
bs->job = NULL;
g_free(job);
bdrv_set_in_use(bs, 0);
error_propagate(errp, local_err);
return NULL;
}
}
return job;
}
static void mirror_complete(BlockJob *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
Error *local_err = NULL;
int ret;
ret = bdrv_open_backing_file(s->target, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return;
}
if (!s->synced) {
error_set(errp, QERR_BLOCK_JOB_NOT_READY,
bdrv_get_device_name(job->bs));
return;
}
/* check the target bs is not blocked and block all operations on it */
if (s->replaces) {
s->to_replace = check_to_replace_node(s->replaces, &local_err);
if (!s->to_replace) {
error_propagate(errp, local_err);
return;
}
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);
}
s->should_complete = true;
block_job_resume(job);
}
void block_job_event_ready(BlockJob *job)
{
qapi_event_send_block_job_ready(job->driver->job_type,
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed, &error_abort);
}
/*
* Returns 0 on success, with *p_list either set to describe snapshot
* information, or NULL because there are no snapshots. Returns -errno on
* error, with *p_list untouched.
*/
int bdrv_query_snapshot_info_list(BlockDriverState *bs,
SnapshotInfoList **p_list,
Error **errp)
{
int i, sn_count;
QEMUSnapshotInfo *sn_tab = NULL;
SnapshotInfoList *info_list, *cur_item = NULL, *head = NULL;
SnapshotInfo *info;
sn_count = bdrv_snapshot_list(bs, &sn_tab);
if (sn_count < 0) {
const char *dev = bdrv_get_device_name(bs);
switch (sn_count) {
case -ENOMEDIUM:
error_setg(errp, "Device '%s' is not inserted", dev);
break;
case -ENOTSUP:
error_setg(errp,
"Device '%s' does not support internal snapshots",
dev);
break;
default:
error_setg_errno(errp, -sn_count,
"Can't list snapshots of device '%s'", dev);
break;
}
return sn_count;
}
for (i = 0; i < sn_count; i++) {
info = g_new0(SnapshotInfo, 1);
info->id = g_strdup(sn_tab[i].id_str);
info->name = g_strdup(sn_tab[i].name);
info->vm_state_size = sn_tab[i].vm_state_size;
info->date_sec = sn_tab[i].date_sec;
info->date_nsec = sn_tab[i].date_nsec;
info->vm_clock_sec = sn_tab[i].vm_clock_nsec / 1000000000;
info->vm_clock_nsec = sn_tab[i].vm_clock_nsec % 1000000000;
info_list = g_new0(SnapshotInfoList, 1);
info_list->value = info;
/* XXX: waiting for the qapi to support qemu-queue.h types */
if (!cur_item) {
head = cur_item = info_list;
} else {
cur_item->next = info_list;
cur_item = info_list;
}
}
g_free(sn_tab);
*p_list = head;
return 0;
}
void block_job_complete(BlockJob *job, Error **errp)
{
if (job->pause_count || job->cancelled || !job->driver->complete) {
error_set(errp, QERR_BLOCK_JOB_NOT_READY,
bdrv_get_device_name(job->bs));
return;
}
job->driver->complete(job, errp);
}
void block_job_event_completed(BlockJob *job, const char *msg)
{
qapi_event_send_block_job_completed(job->driver->job_type,
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed,
!!msg,
msg,
&error_abort);
}
BlockJobInfo *block_job_query(BlockJob *job)
{
BlockJobInfo *info = g_new0(BlockJobInfo, 1);
info->type = g_strdup(BlockJobType_lookup[job->driver->job_type]);
info->device = g_strdup(bdrv_get_device_name(job->bs));
info->len = job->len;
info->busy = job->busy;
info->paused = job->paused;
info->offset = job->offset;
info->speed = job->speed;
info->io_status = job->iostatus;
return info;
}
QObject *qobject_from_block_job(BlockJob *job)
{
return qobject_from_jsonf("{ 'type': %s,"
"'device': %s,"
"'len': %" PRId64 ","
"'offset': %" PRId64 ","
"'speed': %" PRId64 " }",
BlockJobType_lookup[job->driver->job_type],
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed);
}
void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
int64_t speed, BlockCompletionFunc *cb,
void *opaque, Error **errp)
{
BlockJob *job;
if (bs->job) {
error_setg(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
return NULL;
}
bdrv_ref(bs);
job = g_malloc0(driver->instance_size);
error_setg(&job->blocker, "block device is in use by block job: %s",
BlockJobType_lookup[driver->job_type]);
bdrv_op_block_all(bs, job->blocker);
bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
job->driver = driver;
job->id = g_strdup(bdrv_get_device_name(bs));
job->bs = bs;
job->cb = cb;
job->opaque = opaque;
job->busy = true;
bs->job = job;
/* Only set speed when necessary to avoid NotSupported error */
if (speed != 0) {
Error *local_err = NULL;
block_job_set_speed(job, speed, &local_err);
if (local_err) {
block_job_release(bs);
error_propagate(errp, local_err);
return NULL;
}
}
return job;
}
int qdev_prop_set_drive(DeviceState *dev, const char *name,
BlockDriverState *value)
{
Error *errp = NULL;
const char *bdrv_name = value ? bdrv_get_device_name(value) : "";
object_property_set_str(OBJECT(dev), bdrv_name,
name, &errp);
if (errp) {
qerror_report_err(errp);
error_free(errp);
return -1;
}
return 0;
}
BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
BlockdevOnError on_err,
int is_read, int error)
{
BlockErrorAction action;
switch (on_err) {
case BLOCKDEV_ON_ERROR_ENOSPC:
action = (error == ENOSPC) ?
BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_STOP:
action = BLOCK_ERROR_ACTION_STOP;
break;
case BLOCKDEV_ON_ERROR_REPORT:
action = BLOCK_ERROR_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_IGNORE:
action = BLOCK_ERROR_ACTION_IGNORE;
break;
default:
abort();
}
qapi_event_send_block_job_error(bdrv_get_device_name(job->bs),
is_read ? IO_OPERATION_TYPE_READ :
IO_OPERATION_TYPE_WRITE,
action, &error_abort);
if (action == BLOCK_ERROR_ACTION_STOP) {
/* make the pause user visible, which will be resumed from QMP. */
job->user_paused = true;
block_job_pause(job);
block_job_iostatus_set_err(job, error);
if (bs != job->bs) {
bdrv_iostatus_set_err(bs, error);
}
}
return action;
}
static char *print_drive(void *ptr)
{
return g_strdup(bdrv_get_device_name(ptr));
}
static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVVPCState *s = bs->opaque;
int i;
VHDFooter *footer;
VHDDynDiskHeader *dyndisk_header;
uint8_t buf[HEADER_SIZE];
uint32_t checksum;
uint64_t computed_size;
int disk_type = VHD_DYNAMIC;
int ret;
ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE);
if (ret < 0) {
goto fail;
}
footer = (VHDFooter *) s->footer_buf;
if (strncmp(footer->creator, "conectix", 8)) {
int64_t offset = bdrv_getlength(bs->file);
if (offset < 0) {
ret = offset;
goto fail;
} else if (offset < HEADER_SIZE) {
ret = -EINVAL;
goto fail;
}
/* If a fixed disk, the footer is found only at the end of the file */
ret = bdrv_pread(bs->file, offset-HEADER_SIZE, s->footer_buf,
HEADER_SIZE);
if (ret < 0) {
goto fail;
}
if (strncmp(footer->creator, "conectix", 8)) {
error_setg(errp, "invalid VPC image");
ret = -EINVAL;
goto fail;
}
disk_type = VHD_FIXED;
}
checksum = be32_to_cpu(footer->checksum);
footer->checksum = 0;
if (vpc_checksum(s->footer_buf, HEADER_SIZE) != checksum)
fprintf(stderr, "block-vpc: The header checksum of '%s' is "
"incorrect.\n", bs->filename);
/* Write 'checksum' back to footer, or else will leave it with zero. */
footer->checksum = cpu_to_be32(checksum);
// The visible size of a image in Virtual PC depends on the geometry
// rather than on the size stored in the footer (the size in the footer
// is too large usually)
bs->total_sectors = (int64_t)
be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
/* Images that have exactly the maximum geometry are probably bigger and
* would be truncated if we adhered to the geometry for them. Rely on
* footer->current_size for them. */
if (bs->total_sectors == VHD_MAX_GEOMETRY) {
bs->total_sectors = be64_to_cpu(footer->current_size) /
BDRV_SECTOR_SIZE;
}
/* Allow a maximum disk size of approximately 2 TB */
if (bs->total_sectors >= VHD_MAX_SECTORS) {
ret = -EFBIG;
goto fail;
}
if (disk_type == VHD_DYNAMIC) {
ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
HEADER_SIZE);
if (ret < 0) {
goto fail;
}
dyndisk_header = (VHDDynDiskHeader *) buf;
if (strncmp(dyndisk_header->magic, "cxsparse", 8)) {
ret = -EINVAL;
goto fail;
}
s->block_size = be32_to_cpu(dyndisk_header->block_size);
if (!is_power_of_2(s->block_size) || s->block_size < BDRV_SECTOR_SIZE) {
error_setg(errp, "Invalid block size %" PRIu32, s->block_size);
ret = -EINVAL;
goto fail;
}
s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
if ((bs->total_sectors * 512) / s->block_size > 0xffffffffU) {
ret = -EINVAL;
goto fail;
}
if (s->max_table_entries > (VHD_MAX_SECTORS * 512) / s->block_size) {
ret = -EINVAL;
goto fail;
}
computed_size = (uint64_t) s->max_table_entries * s->block_size;
if (computed_size < bs->total_sectors * 512) {
ret = -EINVAL;
goto fail;
}
s->pagetable = qemu_try_blockalign(bs->file, s->max_table_entries * 4);
if (s->pagetable == NULL) {
ret = -ENOMEM;
goto fail;
}
s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable,
s->max_table_entries * 4);
if (ret < 0) {
goto fail;
}
s->free_data_block_offset =
(s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
for (i = 0; i < s->max_table_entries; i++) {
be32_to_cpus(&s->pagetable[i]);
if (s->pagetable[i] != 0xFFFFFFFF) {
int64_t next = (512 * (int64_t) s->pagetable[i]) +
s->bitmap_size + s->block_size;
if (next > s->free_data_block_offset) {
s->free_data_block_offset = next;
}
}
}
if (s->free_data_block_offset > bdrv_getlength(bs->file)) {
error_setg(errp, "block-vpc: free_data_block_offset points after "
"the end of file. The image has been truncated.");
ret = -EINVAL;
goto fail;
}
s->last_bitmap_offset = (int64_t) -1;
#ifdef CACHE
s->pageentry_u8 = g_malloc(512);
s->pageentry_u32 = s->pageentry_u8;
s->pageentry_u16 = s->pageentry_u8;
s->last_pagetable = -1;
#endif
}
qemu_co_mutex_init(&s->lock);
/* Disable migration when VHD images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vpc", bdrv_get_device_name(bs), "live migration");
migrate_add_blocker(s->migration_blocker);
return 0;
fail:
qemu_vfree(s->pagetable);
#ifdef CACHE
g_free(s->pageentry_u8);
#endif
return ret;
}
BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
BlockDriverState *bs, Error **errp)
{
ImageInfo **p_image_info;
BlockDriverState *bs0;
BlockDeviceInfo *info = g_malloc0(sizeof(*info));
info->file = g_strdup(bs->filename);
info->ro = bs->read_only;
info->drv = g_strdup(bs->drv->format_name);
info->encrypted = bs->encrypted;
info->encryption_key_missing = false;
info->cache = g_new(BlockdevCacheInfo, 1);
*info->cache = (BlockdevCacheInfo) {
.writeback = blk ? blk_enable_write_cache(blk) : true,
.direct = !!(bs->open_flags & BDRV_O_NOCACHE),
.no_flush = !!(bs->open_flags & BDRV_O_NO_FLUSH),
};
if (bs->node_name[0]) {
info->has_node_name = true;
info->node_name = g_strdup(bs->node_name);
}
if (bs->backing_file[0]) {
info->has_backing_file = true;
info->backing_file = g_strdup(bs->backing_file);
}
info->detect_zeroes = bs->detect_zeroes;
if (blk && blk_get_public(blk)->throttle_state) {
ThrottleConfig cfg;
throttle_group_get_config(blk, &cfg);
info->bps = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
info->bps_rd = cfg.buckets[THROTTLE_BPS_READ].avg;
info->bps_wr = cfg.buckets[THROTTLE_BPS_WRITE].avg;
info->iops = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
info->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
info->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
info->has_bps_max = cfg.buckets[THROTTLE_BPS_TOTAL].max;
info->bps_max = cfg.buckets[THROTTLE_BPS_TOTAL].max;
info->has_bps_rd_max = cfg.buckets[THROTTLE_BPS_READ].max;
info->bps_rd_max = cfg.buckets[THROTTLE_BPS_READ].max;
info->has_bps_wr_max = cfg.buckets[THROTTLE_BPS_WRITE].max;
info->bps_wr_max = cfg.buckets[THROTTLE_BPS_WRITE].max;
info->has_iops_max = cfg.buckets[THROTTLE_OPS_TOTAL].max;
info->iops_max = cfg.buckets[THROTTLE_OPS_TOTAL].max;
info->has_iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
info->iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
info->iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
info->has_bps_max_length = info->has_bps_max;
info->bps_max_length =
cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
info->has_bps_rd_max_length = info->has_bps_rd_max;
info->bps_rd_max_length =
cfg.buckets[THROTTLE_BPS_READ].burst_length;
info->has_bps_wr_max_length = info->has_bps_wr_max;
info->bps_wr_max_length =
cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
info->has_iops_max_length = info->has_iops_max;
info->iops_max_length =
cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
info->has_iops_rd_max_length = info->has_iops_rd_max;
info->iops_rd_max_length =
cfg.buckets[THROTTLE_OPS_READ].burst_length;
info->has_iops_wr_max_length = info->has_iops_wr_max;
info->iops_wr_max_length =
cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
info->has_iops_size = cfg.op_size;
info->iops_size = cfg.op_size;
info->has_group = true;
info->group = g_strdup(throttle_group_get_name(blk));
}
info->write_threshold = bdrv_write_threshold_get(bs);
bs0 = bs;
p_image_info = &info->image;
info->backing_file_depth = 0;
while (1) {
Error *local_err = NULL;
bdrv_query_image_info(bs0, p_image_info, &local_err);
if (local_err) {
error_propagate(errp, local_err);
qapi_free_BlockDeviceInfo(info);
return NULL;
}
if (bs0->drv && bs0->backing) {
info->backing_file_depth++;
bs0 = bs0->backing->bs;
(*p_image_info)->has_backing_image = true;
p_image_info = &((*p_image_info)->backing_image);
} else {
break;
}
/* Skip automatically inserted nodes that the user isn't aware of for
* query-block (blk != NULL), but not for query-named-block-nodes */
while (blk && bs0->drv && bs0->implicit) {
bs0 = backing_bs(bs0);
assert(bs0);
}
}
return info;
}
/*
* Returns 0 on success, with *p_list either set to describe snapshot
* information, or NULL because there are no snapshots. Returns -errno on
* error, with *p_list untouched.
*/
int bdrv_query_snapshot_info_list(BlockDriverState *bs,
SnapshotInfoList **p_list,
Error **errp)
{
int i, sn_count;
QEMUSnapshotInfo *sn_tab = NULL;
SnapshotInfoList *info_list, *cur_item = NULL, *head = NULL;
SnapshotInfo *info;
sn_count = bdrv_snapshot_list(bs, &sn_tab);
if (sn_count < 0) {
const char *dev = bdrv_get_device_name(bs);
switch (sn_count) {
case -ENOMEDIUM:
error_setg(errp, "Device '%s' is not inserted", dev);
break;
case -ENOTSUP:
error_setg(errp,
"Device '%s' does not support internal snapshots",
dev);
break;
default:
error_setg_errno(errp, -sn_count,
"Can't list snapshots of device '%s'", dev);
break;
}
return sn_count;
}
for (i = 0; i < sn_count; i++) {
info = g_new0(SnapshotInfo, 1);
info->id = g_strdup(sn_tab[i].id_str);
info->name = g_strdup(sn_tab[i].name);
info->vm_state_size = sn_tab[i].vm_state_size;
info->date_sec = sn_tab[i].date_sec;
info->date_nsec = sn_tab[i].date_nsec;
info->vm_clock_sec = sn_tab[i].vm_clock_nsec / 1000000000;
info->vm_clock_nsec = sn_tab[i].vm_clock_nsec % 1000000000;
info_list = g_new0(SnapshotInfoList, 1);
info_list->value = info;
/* XXX: waiting for the qapi to support qemu-queue.h types */
if (!cur_item) {
head = cur_item = info_list;
} else {
cur_item->next = info_list;
cur_item = info_list;
}
}
g_free(sn_tab);
*p_list = head;
return 0;
}
static int print_drive(DeviceState *dev, Property *prop, char *dest, size_t len)
{
BlockDriverState **ptr = qdev_get_prop_ptr(dev, prop);
return snprintf(dest, len, "%s",
*ptr ? bdrv_get_device_name(*ptr) : "<null>");
}
static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
bool query_backing)
{
BlockStats *s;
s = g_malloc0(sizeof(*s));
if (bdrv_get_device_name(bs)[0]) {
s->has_device = true;
s->device = g_strdup(bdrv_get_device_name(bs));
}
if (bdrv_get_node_name(bs)[0]) {
s->has_node_name = true;
s->node_name = g_strdup(bdrv_get_node_name(bs));
}
s->stats = g_malloc0(sizeof(*s->stats));
if (bs->blk) {
BlockAcctStats *stats = blk_get_stats(bs->blk);
BlockAcctTimedStats *ts = NULL;
s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
s->stats->invalid_flush_operations =
stats->invalid_ops[BLOCK_ACCT_FLUSH];
s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
if (s->stats->has_idle_time_ns) {
s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
}
s->stats->account_invalid = stats->account_invalid;
s->stats->account_failed = stats->account_failed;
while ((ts = block_acct_interval_next(stats, ts))) {
BlockDeviceTimedStatsList *timed_stats =
g_malloc0(sizeof(*timed_stats));
BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
timed_stats->next = s->stats->timed_stats;
timed_stats->value = dev_stats;
s->stats->timed_stats = timed_stats;
TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
dev_stats->interval_length = ts->interval_length;
dev_stats->min_rd_latency_ns = timed_average_min(rd);
dev_stats->max_rd_latency_ns = timed_average_max(rd);
dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
dev_stats->min_wr_latency_ns = timed_average_min(wr);
dev_stats->max_wr_latency_ns = timed_average_max(wr);
dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
dev_stats->min_flush_latency_ns = timed_average_min(fl);
dev_stats->max_flush_latency_ns = timed_average_max(fl);
dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
dev_stats->avg_rd_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_READ);
dev_stats->avg_wr_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
}
}
s->stats->wr_highest_offset = bs->wr_highest_offset;
if (bs->file) {
s->has_parent = true;
s->parent = bdrv_query_stats(bs->file->bs, query_backing);
}
if (query_backing && bs->backing) {
s->has_backing = true;
s->backing = bdrv_query_stats(bs->backing->bs, query_backing);
}
return s;
}
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,
bdrv_get_device_name(bs), "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;
/* Header size calculation must not overflow uint32_t */
if (s->header.header_size > UINT32_MAX / s->header.cluster_size) {
return -EINVAL;
}
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 const char *print_drive(void *ptr)
{
return bdrv_get_device_name(ptr);
}
/**
* bdrv_query_image_info:
* @bs: block device to examine
* @p_info: location to store image information
* @errp: location to store error information
*
* Store "flat" image information in @p_info.
*
* "Flat" means it does *not* query backing image information,
* i.e. (*pinfo)->has_backing_image will be set to false and
* (*pinfo)->backing_image to NULL even when the image does in fact have
* a backing image.
*
* @p_info will be set only on success. On error, store error in @errp.
*/
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
Error **errp)
{
int64_t size;
const char *backing_filename;
char backing_filename2[1024];
BlockDriverInfo bdi;
int ret;
Error *err = NULL;
ImageInfo *info;
#ifdef __linux__
int fd, attr;
#endif
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get size of device '%s'",
bdrv_get_device_name(bs));
return;
}
info = g_new0(ImageInfo, 1);
info->filename = g_strdup(bs->filename);
info->format = g_strdup(bdrv_get_format_name(bs));
info->virtual_size = size;
info->actual_size = bdrv_get_allocated_file_size(bs);
info->has_actual_size = info->actual_size >= 0;
if (bdrv_is_encrypted(bs)) {
info->encrypted = true;
info->has_encrypted = true;
}
if (bdrv_get_info(bs, &bdi) >= 0) {
if (bdi.cluster_size != 0) {
info->cluster_size = bdi.cluster_size;
info->has_cluster_size = true;
}
info->dirty_flag = bdi.is_dirty;
info->has_dirty_flag = true;
}
info->format_specific = bdrv_get_specific_info(bs);
info->has_format_specific = info->format_specific != NULL;
#ifdef __linux__
/* get NOCOW info */
fd = qemu_open(bs->filename, O_RDONLY | O_NONBLOCK);
if (fd >= 0) {
if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0 && (attr & FS_NOCOW_FL)) {
info->has_nocow = true;
info->nocow = true;
}
qemu_close(fd);
}
#endif
backing_filename = bs->backing_file;
if (backing_filename[0] != '\0') {
info->backing_filename = g_strdup(backing_filename);
info->has_backing_filename = true;
bdrv_get_full_backing_filename(bs, backing_filename2,
sizeof(backing_filename2));
if (strcmp(backing_filename, backing_filename2) != 0) {
info->full_backing_filename =
g_strdup(backing_filename2);
info->has_full_backing_filename = true;
}
if (bs->backing_format[0]) {
info->backing_filename_format = g_strdup(bs->backing_format);
info->has_backing_filename_format = true;
}
}
ret = bdrv_query_snapshot_info_list(bs, &info->snapshots, &err);
switch (ret) {
case 0:
if (info->snapshots) {
info->has_snapshots = true;
}
break;
/* recoverable error */
case -ENOMEDIUM:
case -ENOTSUP:
error_free(err);
break;
default:
error_propagate(errp, err);
qapi_free_ImageInfo(info);
return;
}
*p_info = info;
}
/**
* bdrv_query_image_info:
* @bs: block device to examine
* @p_info: location to store image information
* @errp: location to store error information
*
* Store "flat" image information in @p_info.
*
* "Flat" means it does *not* query backing image information,
* i.e. (*pinfo)->has_backing_image will be set to false and
* (*pinfo)->backing_image to NULL even when the image does in fact have
* a backing image.
*
* @p_info will be set only on success. On error, store error in @errp.
*/
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
Error **errp)
{
int64_t size;
const char *backing_filename;
BlockDriverInfo bdi;
int ret;
Error *err = NULL;
ImageInfo *info;
aio_context_acquire(bdrv_get_aio_context(bs));
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get size of device '%s'",
bdrv_get_device_name(bs));
goto out;
}
info = g_new0(ImageInfo, 1);
info->filename = g_strdup(bs->filename);
info->format = g_strdup(bdrv_get_format_name(bs));
info->virtual_size = size;
info->actual_size = bdrv_get_allocated_file_size(bs);
info->has_actual_size = info->actual_size >= 0;
if (bdrv_is_encrypted(bs)) {
info->encrypted = true;
info->has_encrypted = true;
}
if (bdrv_get_info(bs, &bdi) >= 0) {
if (bdi.cluster_size != 0) {
info->cluster_size = bdi.cluster_size;
info->has_cluster_size = true;
}
info->dirty_flag = bdi.is_dirty;
info->has_dirty_flag = true;
}
info->format_specific = bdrv_get_specific_info(bs);
info->has_format_specific = info->format_specific != NULL;
backing_filename = bs->backing_file;
if (backing_filename[0] != '\0') {
char *backing_filename2 = g_malloc0(PATH_MAX);
info->backing_filename = g_strdup(backing_filename);
info->has_backing_filename = true;
bdrv_get_full_backing_filename(bs, backing_filename2, PATH_MAX, &err);
if (err) {
/* Can't reconstruct the full backing filename, so we must omit
* this field and apply a Best Effort to this query. */
g_free(backing_filename2);
backing_filename2 = NULL;
error_free(err);
err = NULL;
}
/* Always report the full_backing_filename if present, even if it's the
* same as backing_filename. That they are same is useful info. */
if (backing_filename2) {
info->full_backing_filename = g_strdup(backing_filename2);
info->has_full_backing_filename = true;
}
if (bs->backing_format[0]) {
info->backing_filename_format = g_strdup(bs->backing_format);
info->has_backing_filename_format = true;
}
g_free(backing_filename2);
}
ret = bdrv_query_snapshot_info_list(bs, &info->snapshots, &err);
switch (ret) {
case 0:
if (info->snapshots) {
info->has_snapshots = true;
}
break;
/* recoverable error */
case -ENOMEDIUM:
case -ENOTSUP:
error_free(err);
break;
default:
error_propagate(errp, err);
qapi_free_ImageInfo(info);
goto out;
}
*p_info = info;
out:
aio_context_release(bdrv_get_aio_context(bs));
}
/**
* bdrv_query_image_info:
* @bs: block device to examine
* @p_info: location to store image information
* @errp: location to store error information
*
* Store "flat" image information in @p_info.
*
* "Flat" means it does *not* query backing image information,
* i.e. (*pinfo)->has_backing_image will be set to false and
* (*pinfo)->backing_image to NULL even when the image does in fact have
* a backing image.
*
* @p_info will be set only on success. On error, store error in @errp.
*/
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
Error **errp)
{
int64_t size;
const char *backing_filename;
BlockDriverInfo bdi;
int ret;
Error *err = NULL;
ImageInfo *info;
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get size of device '%s'",
bdrv_get_device_name(bs));
return;
}
info = g_new0(ImageInfo, 1);
info->filename = g_strdup(bs->filename);
info->format = g_strdup(bdrv_get_format_name(bs));
info->virtual_size = size;
info->actual_size = bdrv_get_allocated_file_size(bs);
info->has_actual_size = info->actual_size >= 0;
if (bdrv_is_encrypted(bs)) {
info->encrypted = true;
info->has_encrypted = true;
}
if (bdrv_get_info(bs, &bdi) >= 0) {
if (bdi.cluster_size != 0) {
info->cluster_size = bdi.cluster_size;
info->has_cluster_size = true;
}
info->dirty_flag = bdi.is_dirty;
info->has_dirty_flag = true;
}
info->format_specific = bdrv_get_specific_info(bs);
info->has_format_specific = info->format_specific != NULL;
backing_filename = bs->backing_file;
if (backing_filename[0] != '\0') {
char *backing_filename2 = g_malloc0(PATH_MAX);
info->backing_filename = g_strdup(backing_filename);
info->has_backing_filename = true;
bdrv_get_full_backing_filename(bs, backing_filename2, PATH_MAX, &err);
if (err) {
error_propagate(errp, err);
qapi_free_ImageInfo(info);
g_free(backing_filename2);
return;
}
if (strcmp(backing_filename, backing_filename2) != 0) {
info->full_backing_filename =
g_strdup(backing_filename2);
info->has_full_backing_filename = true;
}
if (bs->backing_format[0]) {
info->backing_filename_format = g_strdup(bs->backing_format);
info->has_backing_filename_format = true;
}
g_free(backing_filename2);
}
ret = bdrv_query_snapshot_info_list(bs, &info->snapshots, &err);
switch (ret) {
case 0:
if (info->snapshots) {
info->has_snapshots = true;
}
break;
/* recoverable error */
case -ENOMEDIUM:
case -ENOTSUP:
error_free(err);
break;
default:
error_propagate(errp, err);
qapi_free_ImageInfo(info);
return;
}
*p_info = info;
}
