static int64_t block_crypto_getlength(BlockDriverState *bs)
{
BlockCrypto *crypto = bs->opaque;
int64_t len = bdrv_getlength(bs->file->bs);
ssize_t offset = qcrypto_block_get_payload_offset(crypto->block);
len -= offset;
return len;
}
static int nand_device_init(SysBusDevice *dev)
{
int pagesize;
NANDFlashState *s = FROM_SYSBUS(NANDFlashState, dev);
s->buswidth = nand_flash_ids[s->chip_id].width >> 3;
s->size = nand_flash_ids[s->chip_id].size << 20;
if (nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) {
s->page_shift = 11;
s->erase_shift = 6;
} else {
s->page_shift = nand_flash_ids[s->chip_id].page_shift;
s->erase_shift = nand_flash_ids[s->chip_id].erase_shift;
}
switch (1 << s->page_shift) {
case 256:
nand_init_256(s);
break;
case 512:
nand_init_512(s);
break;
case 2048:
nand_init_2048(s);
break;
default:
error_report("Unsupported NAND block size");
return -1;
}
pagesize = 1 << s->oob_shift;
s->mem_oob = 1;
if (s->bdrv) {
if (bdrv_is_read_only(s->bdrv)) {
error_report("Can't use a read-only drive");
return -1;
}
if (bdrv_getlength(s->bdrv) >=
(s->pages << s->page_shift) + (s->pages << s->oob_shift)) {
pagesize = 0;
s->mem_oob = 0;
}
} else {
pagesize += 1 << s->page_shift;
}
if (pagesize) {
s->storage = (uint8_t *) memset(g_malloc(s->pages * pagesize),
0xff, s->pages * pagesize);
}
/* Give s->ioaddr a sane value in case we save state before it is used. */
s->ioaddr = s->io;
return 0;
}
NBDExport *nbd_export_new(BlockDriverState *bs, off_t dev_offset,
off_t size, uint32_t nbdflags)
{
NBDExport *exp = g_malloc0(sizeof(NBDExport));
QSIMPLEQ_INIT(&exp->requests);
exp->bs = bs;
exp->dev_offset = dev_offset;
exp->nbdflags = nbdflags;
exp->size = size == -1 ? bdrv_getlength(bs) : size;
return exp;
}
static int length_f(int argc, char **argv)
{
int64_t size;
char s1[64];
size = bdrv_getlength(bs);
if (size < 0) {
printf("getlength: %s\n", strerror(-size));
return 0;
}
cvtstr(size, s1, sizeof(s1));
printf("%s\n", s1);
return 0;
}
static int check_dir_entry(BlockDriverState *bs, Qcow2BitmapDirEntry *entry)
{
BDRVQcow2State *s = bs->opaque;
uint64_t phys_bitmap_bytes;
int64_t len;
bool fail = (entry->bitmap_table_size == 0) ||
(entry->bitmap_table_offset == 0) ||
(entry->bitmap_table_offset % s->cluster_size) ||
(entry->bitmap_table_size > BME_MAX_TABLE_SIZE) ||
(entry->granularity_bits > BME_MAX_GRANULARITY_BITS) ||
(entry->granularity_bits < BME_MIN_GRANULARITY_BITS) ||
(entry->flags & BME_RESERVED_FLAGS) ||
(entry->name_size > BME_MAX_NAME_SIZE) ||
(entry->type != BT_DIRTY_TRACKING_BITMAP);
if (fail) {
return -EINVAL;
}
phys_bitmap_bytes = (uint64_t)entry->bitmap_table_size * s->cluster_size;
len = bdrv_getlength(bs);
if (len < 0) {
return len;
}
if (phys_bitmap_bytes > BME_MAX_PHYS_SIZE) {
return -EINVAL;
}
if (!(entry->flags & BME_FLAG_IN_USE) &&
(len > ((phys_bitmap_bytes * 8) << entry->granularity_bits)))
{
/*
* We've loaded a valid bitmap (IN_USE not set) or we are going to
* store a valid bitmap, but the allocated bitmap table size is not
* enough to store this bitmap.
*
* Note, that it's OK to have an invalid bitmap with invalid size due
* to a bitmap that was not correctly saved after image resize.
*/
return -EINVAL;
}
return 0;
}
static int check_constraints_on_bitmap(BlockDriverState *bs,
const char *name,
uint32_t granularity,
Error **errp)
{
BDRVQcow2State *s = bs->opaque;
int granularity_bits = ctz32(granularity);
int64_t len = bdrv_getlength(bs);
assert(granularity > 0);
assert((granularity & (granularity - 1)) == 0);
if (len < 0) {
error_setg_errno(errp, -len, "Failed to get size of '%s'",
bdrv_get_device_or_node_name(bs));
return len;
}
if (granularity_bits > BME_MAX_GRANULARITY_BITS) {
error_setg(errp, "Granularity exceeds maximum (%llu bytes)",
1ULL << BME_MAX_GRANULARITY_BITS);
return -EINVAL;
}
if (granularity_bits < BME_MIN_GRANULARITY_BITS) {
error_setg(errp, "Granularity is under minimum (%llu bytes)",
1ULL << BME_MIN_GRANULARITY_BITS);
return -EINVAL;
}
if ((len > (uint64_t)BME_MAX_PHYS_SIZE << granularity_bits) ||
(len > (uint64_t)BME_MAX_TABLE_SIZE * s->cluster_size <<
granularity_bits))
{
error_setg(errp, "Too much space will be occupied by the bitmap. "
"Use larger granularity");
return -EINVAL;
}
if (strlen(name) > BME_MAX_NAME_SIZE) {
error_setg(errp, "Name length exceeds maximum (%u characters)",
BME_MAX_NAME_SIZE);
return -EINVAL;
}
return 0;
}
static int64_t dmg_find_koly_offset(BdrvChild *file, Error **errp)
{
BlockDriverState *file_bs = file->bs;
int64_t length;
int64_t offset = 0;
uint8_t buffer[515];
int i, ret;
/* bdrv_getlength returns a multiple of block size (512), rounded up. Since
* dmg images can have odd sizes, try to look for the "koly" magic which
* marks the begin of the UDIF trailer (512 bytes). This magic can be found
* in the last 511 bytes of the second-last sector or the first 4 bytes of
* the last sector (search space: 515 bytes) */
length = bdrv_getlength(file_bs);
if (length < 0) {
error_setg_errno(errp, -length,
"Failed to get file size while reading UDIF trailer");
return length;
} else if (length < 512) {
error_setg(errp, "dmg file must be at least 512 bytes long");
return -EINVAL;
}
if (length > 511 + 512) {
offset = length - 511 - 512;
}
length = length < 515 ? length : 515;
ret = bdrv_pread(file, offset, buffer, length);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed while reading UDIF trailer");
return ret;
}
for (i = 0; i < length - 3; i++) {
if (buffer[i] == 'k' && buffer[i+1] == 'o' &&
buffer[i+2] == 'l' && buffer[i+3] == 'y') {
return offset + i;
}
}
error_setg(errp, "Could not locate UDIF trailer in dmg file");
return -EINVAL;
}
static int spapr_nvram_init(VIOsPAPRDevice *dev)
{
sPAPRNVRAM *nvram = VIO_SPAPR_NVRAM(dev);
if (nvram->drive) {
nvram->size = bdrv_getlength(nvram->drive);
} else {
nvram->size = DEFAULT_NVRAM_SIZE;
nvram->buf = g_malloc0(nvram->size);
}
if ((nvram->size < MIN_NVRAM_SIZE) || (nvram->size > MAX_NVRAM_SIZE)) {
fprintf(stderr, "spapr-nvram must be between %d and %d bytes in size\n",
MIN_NVRAM_SIZE, MAX_NVRAM_SIZE);
return -1;
}
spapr_rtas_register(RTAS_NVRAM_FETCH, "nvram-fetch", rtas_nvram_fetch);
spapr_rtas_register(RTAS_NVRAM_STORE, "nvram-store", rtas_nvram_store);
return 0;
}
/* coalesce internal state, copy to pci i/o region 0
*/
static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
struct virtio_blk_config blkcfg;
uint64_t capacity;
int blk_size = s->conf->logical_block_size;
bdrv_get_geometry(s->bs, &capacity);
memset(&blkcfg, 0, sizeof(blkcfg));
virtio_stq_p(vdev, &blkcfg.capacity, capacity);
virtio_stl_p(vdev, &blkcfg.seg_max, 128 - 2);
virtio_stw_p(vdev, &blkcfg.cylinders, s->conf->cyls);
virtio_stl_p(vdev, &blkcfg.blk_size, blk_size);
virtio_stw_p(vdev, &blkcfg.min_io_size, s->conf->min_io_size / blk_size);
virtio_stw_p(vdev, &blkcfg.opt_io_size, s->conf->opt_io_size / blk_size);
blkcfg.heads = s->conf->heads;
/*
* We must ensure that the block device capacity is a multiple of
* the logical block size. If that is not the case, let's use
* sector_mask to adopt the geometry to have a correct picture.
* For those devices where the capacity is ok for the given geometry
* we don't touch the sector value of the geometry, since some devices
* (like s390 dasd) need a specific value. Here the capacity is already
* cyls*heads*secs*blk_size and the sector value is not block size
* divided by 512 - instead it is the amount of blk_size blocks
* per track (cylinder).
*/
if (bdrv_getlength(s->bs) / s->conf->heads / s->conf->secs % blk_size) {
blkcfg.sectors = s->conf->secs & ~s->sector_mask;
} else {
blkcfg.sectors = s->conf->secs;
}
blkcfg.size_max = 0;
blkcfg.physical_block_exp = get_physical_block_exp(s->conf);
blkcfg.alignment_offset = 0;
blkcfg.wce = bdrv_enable_write_cache(s->bs);
memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
}
static uint32_t allocate_chunk (BlockDriverState * bs)
{
BDRVFvdState *s = bs->opaque;
/* Check if there is sufficient storage space. */
if (s->used_storage + s->chunk_size > s->data_storage) {
if (s->add_storage_cmd) {
if (system (s->add_storage_cmd)) {
fprintf (stderr, "Error in executing %s\n", s->add_storage_cmd);
}
} else {
/* If the image is stored on a file system, the image file size
* can be increased by bdrv_truncate. */
int64_t new_size = (s->data_offset + s->used_storage +
s->storage_grow_unit) * 512;
bdrv_truncate (s->fvd_data, new_size);
}
/* Check how much storage is available now. */
int64_t size = bdrv_getlength (s->fvd_data);
if (size < 0) {
fprintf (stderr, "Error in bdrv_getlength(%s)\n", bs->filename);
return EMPTY_TABLE;
}
s->data_storage = size / 512 - s->data_offset;
if (s->used_storage + s->chunk_size > s->data_storage) {
fprintf (stderr, "Could not allocate more storage space.\n");
return EMPTY_TABLE;
}
QDEBUG ("Increased storage to %" PRId64 " bytes.\n", size);
}
uint32_t allocated_chunk_id = s->used_storage / s->chunk_size;
s->used_storage += s->chunk_size;
return allocated_chunk_id;
}
static int blk_init(struct XenDevice *xendev)
{
struct XenBlkDev *blkdev = container_of(xendev, struct XenBlkDev, xendev);
int index, qflags, have_barriers, info = 0;
char *h;
/* read xenstore entries */
if (blkdev->params == NULL) {
blkdev->params = xenstore_read_be_str(&blkdev->xendev, "params");
h = strchr(blkdev->params, ':');
if (h != NULL) {
blkdev->fileproto = blkdev->params;
blkdev->filename = h+1;
*h = 0;
} else {
blkdev->fileproto = "<unset>";
blkdev->filename = blkdev->params;
}
}
if (blkdev->mode == NULL)
blkdev->mode = xenstore_read_be_str(&blkdev->xendev, "mode");
if (blkdev->type == NULL)
blkdev->type = xenstore_read_be_str(&blkdev->xendev, "type");
if (blkdev->dev == NULL)
blkdev->dev = xenstore_read_be_str(&blkdev->xendev, "dev");
if (blkdev->devtype == NULL)
blkdev->devtype = xenstore_read_be_str(&blkdev->xendev, "device-type");
/* do we have all we need? */
if (blkdev->params == NULL ||
blkdev->mode == NULL ||
blkdev->type == NULL ||
blkdev->dev == NULL)
return -1;
/* read-only ? */
if (strcmp(blkdev->mode, "w") == 0) {
qflags = BDRV_O_RDWR;
} else {
qflags = 0;
info |= VDISK_READONLY;
}
/* cdrom ? */
if (blkdev->devtype && !strcmp(blkdev->devtype, "cdrom"))
info |= VDISK_CDROM;
/* init qemu block driver */
index = (blkdev->xendev.dev - 202 * 256) / 16;
blkdev->dinfo = drive_get(IF_XEN, 0, index);
if (!blkdev->dinfo) {
/* setup via xenbus -> create new block driver instance */
xen_be_printf(&blkdev->xendev, 2, "create new bdrv (xenbus setup)\n");
blkdev->bs = bdrv_new(blkdev->dev);
if (bdrv_open(blkdev->bs, blkdev->filename, qflags,
bdrv_find_whitelisted_format(blkdev->fileproto)) != 0) {
bdrv_delete(blkdev->bs);
return -1;
}
} else {
/* setup via qemu cmdline -> already setup for us */
xen_be_printf(&blkdev->xendev, 2, "get configured bdrv (cmdline setup)\n");
blkdev->bs = blkdev->dinfo->bdrv;
}
blkdev->file_blk = BLOCK_SIZE;
blkdev->file_size = bdrv_getlength(blkdev->bs);
if (blkdev->file_size < 0) {
xen_be_printf(&blkdev->xendev, 1, "bdrv_getlength: %d (%s) | drv %s\n",
(int)blkdev->file_size, strerror(-blkdev->file_size),
blkdev->bs->drv ? blkdev->bs->drv->format_name : "-");
blkdev->file_size = 0;
}
have_barriers = blkdev->bs->drv && blkdev->bs->drv->bdrv_flush ? 1 : 0;
xen_be_printf(xendev, 1, "type \"%s\", fileproto \"%s\", filename \"%s\","
" size %" PRId64 " (%" PRId64 " MB)\n",
blkdev->type, blkdev->fileproto, blkdev->filename,
blkdev->file_size, blkdev->file_size >> 20);
/* fill info */
xenstore_write_be_int(&blkdev->xendev, "feature-barrier", have_barriers);
xenstore_write_be_int(&blkdev->xendev, "info", info);
xenstore_write_be_int(&blkdev->xendev, "sector-size", blkdev->file_blk);
xenstore_write_be_int(&blkdev->xendev, "sectors",
blkdev->file_size / blkdev->file_blk);
return 0;
}
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
MirrorExitData *data;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, 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) {
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;
}
mirror_free_init(s);
last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
if (!s->is_none_mode) {
/* First part, loop on the sectors and initialize the dirty bitmap. */
BlockDriverState *base = s->base;
bool mark_all_dirty = s->base == NULL && !bdrv_has_zero_init(s->target);
for (sector_num = 0; sector_num < end; ) {
/* Just to make sure we are not exceeding int limit. */
int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS,
end - sector_num);
int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
if (now - last_pause_ns > SLICE_TIME) {
last_pause_ns = now;
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0);
}
if (block_job_is_cancelled(&s->common)) {
goto immediate_exit;
}
ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n);
if (ret < 0) {
goto immediate_exit;
}
assert(n > 0);
if (ret == 1 || mark_all_dirty) {
bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n);
}
sector_num += n;
}
}
static void perform_test(const char *truth_file, const char *test_file,
const char *format, int compare_before,
int compare_after)
{
int flags, i;
bs = bdrv_new ("hda");
if (!bs) {
die ("bdrv_new failed\n");
}
BlockDriver *drv = NULL;
if (format) {
drv = bdrv_find_format (format);
if (!drv) {
die ("Found no driver for format '%s'.\n", format);
}
}
flags = BDRV_O_RDWR | BDRV_O_CACHE_WB;
if (bdrv_open (bs, test_file, flags, drv) < 0) {
die ("Failed to open '%s'\n", test_file);
}
fd = open (truth_file, O_RDWR | O_LARGEFILE, 0);
if (fd < 0) {
perror ("open");
die ("Failed to open '%s'\n", truth_file);
}
int64_t l0 = lseek (fd, 0, SEEK_END);
int64_t l1 = bdrv_getlength (bs);
if (l0 < 0 || l1 < 0 || l0 < l1) {
die ("Mismatch: truth image %s length %" PRId64 ", test image %s "
"length %" PRId64 "\n", truth_file, l0, test_file, l1);
}
total_sectors = l1 / 512;
if (total_sectors <= 1) {
die ("Total sectors: %" PRId64 "\n", total_sectors);
}
io_size /= 512;
if (io_size <= 0) {
io_size = 1;
} else if (io_size > total_sectors / 2) {
io_size = total_sectors / 2;
}
if (compare_before) {
if (compare_full_images ()) {
die ("The original two files do not match.\n");
}
}
if (round > 0) {
/* Create testers. */
testers = g_malloc(sizeof(RandomIO) * parallel);
for (i = 0; i < parallel; i++) {
RandomIO *r = &testers[i];
r->test_buf = qemu_blockalign (bs, io_size * 512);
if (posix_memalign ((void **) &r->truth_buf, 512, io_size * 512)) {
die ("posix_memalign");
}
r->qiov.iov = g_malloc(sizeof(struct iovec) * max_iov);
r->sector_num = 0;
r->nb_sectors = 0;
r->type = OP_READ;
r->tester = i;
}
for (i = 0; i < parallel; i++) {
perform_next_io (&testers[i]);
}
}
sim_all_tasks (); /* Run tests. */
if (round > 0) {
/* Create testers. */
if (compare_after) {
if (compare_full_images ()) {
die ("The two files do not match after I/O operations.\n");
}
}
for (i = 0; i < parallel; i++) {
RandomIO *r = &testers[i];
qemu_vfree (r->test_buf);
free (r->truth_buf);
g_free(r->qiov.iov);
}
g_free(testers);
}
printf ("Test process %d finished successfully\n", getpid ());
int fvd = (strncmp (bs->drv->format_name, "fvd", 3) == 0);
bdrv_delete (bs);
if (fvd) {
fvd_check_memory_usage ();
}
close (fd);
}
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);
}
/**
* 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 image size '%s'",
bs->exact_filename);
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;
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;
}
static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVDMGState *s = bs->opaque;
uint64_t info_begin, info_end, last_in_offset, last_out_offset;
uint32_t count, tmp;
uint32_t max_compressed_size = 1, max_sectors_per_chunk = 1, i;
int64_t offset;
int ret;
bs->read_only = 1;
s->n_chunks = 0;
s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
/* read offset of info blocks */
offset = bdrv_getlength(bs->file);
if (offset < 0) {
ret = offset;
goto fail;
}
offset -= 0x1d8;
ret = read_uint64(bs, offset, &info_begin);
if (ret < 0) {
goto fail;
} else if (info_begin == 0) {
ret = -EINVAL;
goto fail;
}
ret = read_uint32(bs, info_begin, &tmp);
if (ret < 0) {
goto fail;
} else if (tmp != 0x100) {
ret = -EINVAL;
goto fail;
}
ret = read_uint32(bs, info_begin + 4, &count);
if (ret < 0) {
goto fail;
} else if (count == 0) {
ret = -EINVAL;
goto fail;
}
info_end = info_begin + count;
offset = info_begin + 0x100;
/* read offsets */
last_in_offset = last_out_offset = 0;
while (offset < info_end) {
uint32_t type;
ret = read_uint32(bs, offset, &count);
if (ret < 0) {
goto fail;
} else if (count == 0) {
ret = -EINVAL;
goto fail;
}
offset += 4;
ret = read_uint32(bs, offset, &type);
if (ret < 0) {
goto fail;
}
if (type == 0x6d697368 && count >= 244) {
size_t new_size;
uint32_t chunk_count;
offset += 4;
offset += 200;
chunk_count = (count - 204) / 40;
new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
s->types = g_realloc(s->types, new_size / 2);
s->offsets = g_realloc(s->offsets, new_size);
s->lengths = g_realloc(s->lengths, new_size);
s->sectors = g_realloc(s->sectors, new_size);
s->sectorcounts = g_realloc(s->sectorcounts, new_size);
for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
ret = read_uint32(bs, offset, &s->types[i]);
if (ret < 0) {
goto fail;
}
offset += 4;
if (s->types[i] != 0x80000005 && s->types[i] != 1 &&
s->types[i] != 2) {
if (s->types[i] == 0xffffffff && i > 0) {
last_in_offset = s->offsets[i - 1] + s->lengths[i - 1];
last_out_offset = s->sectors[i - 1] +
s->sectorcounts[i - 1];
}
chunk_count--;
i--;
offset += 36;
continue;
}
offset += 4;
ret = read_uint64(bs, offset, &s->sectors[i]);
if (ret < 0) {
goto fail;
}
s->sectors[i] += last_out_offset;
offset += 8;
ret = read_uint64(bs, offset, &s->sectorcounts[i]);
if (ret < 0) {
goto fail;
}
offset += 8;
if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
error_report("sector count %" PRIu64 " for chunk %" PRIu32
" is larger than max (%u)",
s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
ret = -EINVAL;
goto fail;
}
ret = read_uint64(bs, offset, &s->offsets[i]);
if (ret < 0) {
goto fail;
}
s->offsets[i] += last_in_offset;
offset += 8;
ret = read_uint64(bs, offset, &s->lengths[i]);
if (ret < 0) {
goto fail;
}
offset += 8;
if (s->lengths[i] > DMG_LENGTHS_MAX) {
error_report("length %" PRIu64 " for chunk %" PRIu32
" is larger than max (%u)",
s->lengths[i], i, DMG_LENGTHS_MAX);
ret = -EINVAL;
goto fail;
}
update_max_chunk_size(s, i, &max_compressed_size,
&max_sectors_per_chunk);
}
s->n_chunks += chunk_count;
}
}
/* initialize zlib engine */
s->compressed_chunk = qemu_try_blockalign(bs->file,
max_compressed_size + 1);
s->uncompressed_chunk = qemu_try_blockalign(bs->file,
512 * 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 int64_t raw_getlength(BlockDriverState *bs)
{
return bdrv_getlength(bs->file);
}
int initNbd(char* filename)
{
BlockDriverState *bs;
off_t dev_offset = 0;
uint32_t nbdflags = 0;
bool disconnect = false;
const char *bindto = "0.0.0.0";
char *device = NULL;
int port = NBD_DEFAULT_PORT;
off_t fd_size;
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 fd;
int persistent = 0;
pthread_t client_thread;
/* 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);
// 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 | BDRV_O_CACHE_WB;
// 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':
// 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 '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]);
// }
/*
Start a daemon!
Use client thread to start daemon and write errors;
Use parent thread to wait for and write error messages.
*/
// if (device && !verbose) {
// int stderr_fd[2];
// pid_t pid;
// int ret;
//
// //Setting up Pipe, close after succeeded.
// 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.
// */
// //Fork returns 0 for child process and the pid of child process for the parent process
// pid = fork();
// 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);
// }
// }
//
// //Set sock path... But what is sock path???
// if (device != NULL && sockpath == NULL) {
// sockpath = g_malloc(128);
// snprintf(sockpath, 128, SOCKET_PATH, basename(device));
// }
//Init a block device!
bdrv_init();
atexit(bdrv_close_all);
//Malloc a new block device state
bs = bdrv_new("hda");
srcpath = filename;
if ((ret = bdrv_open(bs, srcpath, flags, NULL)) < 0) {
errno = -ret;
err(EXIT_FAILURE, "Failed to bdrv_open '%s'", srcpath);
}
fd_size = bdrv_getlength(bs);
if (partition != -1) {
ret = find_partition(bs, partition, &dev_offset, &fd_size);
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE, "Could not find partition %d", partition);
}
}
exp = nbd_export_new(bs, dev_offset, fd_size, nbdflags);
if (sockpath) {
fd = unix_socket_incoming(sockpath);
fprintf(stderr, "NBD device running on sock path :%s\n", sockpath);
} else {
fd = tcp_socket_incoming(bindto, port);
fprintf(stderr, "NBD device running on port :%i\n", port);
}
if (fd < 0) {
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));
}
qemu_init_main_loop();
qemu_set_fd_handler2(fd, nbd_can_accept, nbd_accept, NULL,
(void *)(uintptr_t)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");
}
do {
main_loop_wait(false);
} while (!sigterm_reported && (persistent || !nbd_started || nb_fds > 0));
nbd_export_close(exp);
if (sockpath) {
unlink(sockpath);
}
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
static int64_t cor_getlength(BlockDriverState *bs)
{
return bdrv_getlength(bs->file->bs);
}
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;
uint64_t pagetable_size;
int disk_type = VHD_DYNAMIC;
int ret;
ret = bdrv_pread(bs->file->bs, 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->bs);
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->bs, 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->bs, 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;
}
if (s->max_table_entries > SIZE_MAX / 4 ||
s->max_table_entries > (int) INT_MAX / 4) {
error_setg(errp, "Max Table Entries too large (%" PRId32 ")",
s->max_table_entries);
ret = -EINVAL;
goto fail;
}
pagetable_size = (uint64_t) s->max_table_entries * 4;
s->pagetable = qemu_try_blockalign(bs->file->bs, pagetable_size);
if (s->pagetable == NULL) {
ret = -ENOMEM;
goto fail;
}
s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
ret = bdrv_pread(bs->file->bs, s->bat_offset, s->pagetable,
pagetable_size);
if (ret < 0) {
goto fail;
}
s->free_data_block_offset =
ROUND_UP(s->bat_offset + pagetable_size, 512);
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->bs)) {
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_setg(&s->migration_blocker, "The vpc format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
migrate_add_blocker(s->migration_blocker);
return 0;
fail:
qemu_vfree(s->pagetable);
#ifdef CACHE
g_free(s->pageentry_u8);
#endif
return ret;
}
static int dmg_open(BlockDriverState *bs, int flags)
{
BDRVDMGState *s = bs->opaque;
uint64_t info_begin,info_end,last_in_offset,last_out_offset;
uint32_t count, tmp;
uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
int64_t offset;
int ret;
bs->read_only = 1;
s->n_chunks = 0;
s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
/* read offset of info blocks */
offset = bdrv_getlength(bs->file);
if (offset < 0) {
ret = offset;
goto fail;
}
offset -= 0x1d8;
ret = read_uint64(bs, offset, &info_begin);
if (ret < 0) {
goto fail;
} else if (info_begin == 0) {
ret = -EINVAL;
goto fail;
}
ret = read_uint32(bs, info_begin, &tmp);
if (ret < 0) {
goto fail;
} else if (tmp != 0x100) {
ret = -EINVAL;
goto fail;
}
ret = read_uint32(bs, info_begin + 4, &count);
if (ret < 0) {
goto fail;
} else if (count == 0) {
ret = -EINVAL;
goto fail;
}
info_end = info_begin + count;
offset = info_begin + 0x100;
/* read offsets */
last_in_offset = last_out_offset = 0;
while (offset < info_end) {
uint32_t type;
ret = read_uint32(bs, offset, &count);
if (ret < 0) {
goto fail;
} else if (count == 0) {
ret = -EINVAL;
goto fail;
}
offset += 4;
ret = read_uint32(bs, offset, &type);
if (ret < 0) {
goto fail;
}
if (type == 0x6d697368 && count >= 244) {
int new_size, chunk_count;
offset += 4;
offset += 200;
chunk_count = (count-204)/40;
new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
s->types = g_realloc(s->types, new_size/2);
s->offsets = g_realloc(s->offsets, new_size);
s->lengths = g_realloc(s->lengths, new_size);
s->sectors = g_realloc(s->sectors, new_size);
s->sectorcounts = g_realloc(s->sectorcounts, new_size);
for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
ret = read_uint32(bs, offset, &s->types[i]);
if (ret < 0) {
goto fail;
}
offset += 4;
if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
if(s->types[i]==0xffffffff) {
last_in_offset = s->offsets[i-1]+s->lengths[i-1];
last_out_offset = s->sectors[i-1]+s->sectorcounts[i-1];
}
chunk_count--;
i--;
offset += 36;
continue;
}
offset += 4;
ret = read_uint64(bs, offset, &s->sectors[i]);
if (ret < 0) {
goto fail;
}
s->sectors[i] += last_out_offset;
offset += 8;
ret = read_uint64(bs, offset, &s->sectorcounts[i]);
if (ret < 0) {
goto fail;
}
offset += 8;
ret = read_uint64(bs, offset, &s->offsets[i]);
if (ret < 0) {
goto fail;
}
s->offsets[i] += last_in_offset;
offset += 8;
ret = read_uint64(bs, offset, &s->lengths[i]);
if (ret < 0) {
goto fail;
}
offset += 8;
if(s->lengths[i]>max_compressed_size)
max_compressed_size = s->lengths[i];
if(s->sectorcounts[i]>max_sectors_per_chunk)
max_sectors_per_chunk = s->sectorcounts[i];
}
s->n_chunks+=chunk_count;
}
}
/* initialize zlib engine */
s->compressed_chunk = g_malloc(max_compressed_size+1);
s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
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);
g_free(s->compressed_chunk);
g_free(s->uncompressed_chunk);
return ret;
}
int main(int argc, char **argv)
{
BlockDriverState *bs;
BlockDriver *drv;
off_t dev_offset = 0;
uint32_t nbdflags = 0;
bool disconnect = false;
const char *bindto = "0.0.0.0";
char *device = NULL;
int port = NBD_DEFAULT_PORT;
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 },
#ifdef CONFIG_LINUX_AIO
{ "aio", 1, NULL, QEMU_NBD_OPT_AIO },
#endif
{ "discard", 1, NULL, QEMU_NBD_OPT_DISCARD },
{ "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;
int li;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret;
int fd;
bool seen_cache = false;
bool seen_discard = false;
#ifdef CONFIG_LINUX_AIO
bool seen_aio = false;
#endif
pthread_t client_thread;
const char *fmt = NULL;
Error *local_err = 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;
#ifdef CONFIG_LINUX_AIO
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;
#endif
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 '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 'l':
if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
sn_opts = qemu_opts_parse(&internal_snapshot_opts, optarg, 0);
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) {
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));
}
qemu_init_main_loop();
bdrv_init();
atexit(bdrv_close_all);
if (fmt) {
drv = bdrv_find_format(fmt);
if (!drv) {
errx(EXIT_FAILURE, "Unknown file format '%s'", fmt);
}
} else {
drv = NULL;
}
bs = bdrv_new("hda");
srcpath = argv[optind];
ret = bdrv_open(&bs, srcpath, NULL, NULL, flags, drv, &local_err);
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE, "Failed to bdrv_open '%s': %s", argv[optind],
error_get_pretty(local_err));
}
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));
}
fd_size = bdrv_getlength(bs);
if (partition != -1) {
ret = find_partition(bs, partition, &dev_offset, &fd_size);
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE, "Could not find partition %d", partition);
}
}
exp = nbd_export_new(bs, dev_offset, fd_size, nbdflags, nbd_export_closed);
if (sockpath) {
fd = unix_socket_incoming(sockpath);
} else {
fd = tcp_socket_incoming(bindto, port);
}
if (fd < 0) {
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));
}
qemu_set_fd_handler2(fd, nbd_can_accept, nbd_accept, NULL,
(void *)(uintptr_t)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);
bdrv_close(bs);
if (sockpath) {
unlink(sockpath);
}
if (sn_opts) {
qemu_opts_del(sn_opts);
}
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
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;
}
/* Flush the entire log (as described by 'logs') to the VHDX image
* file, and then set the log to 'empty' status once complete.
*
* The log entries should be validate prior to flushing */
static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
VHDXLogSequence *logs)
{
int ret = 0;
int i;
uint32_t cnt, sectors_read;
uint64_t new_file_size;
void *data = NULL;
VHDXLogDescEntries *desc_entries = NULL;
VHDXLogEntryHeader hdr_tmp = { 0 };
cnt = logs->count;
data = qemu_blockalign(bs, VHDX_LOG_SECTOR_SIZE);
ret = vhdx_user_visible_write(bs, s);
if (ret < 0) {
goto exit;
}
/* each iteration represents one log sequence, which may span multiple
* sectors */
while (cnt--) {
ret = vhdx_log_peek_hdr(bs, &logs->log, &hdr_tmp);
if (ret < 0) {
goto exit;
}
/* if the log shows a FlushedFileOffset larger than our current file
* size, then that means the file has been truncated / corrupted, and
* we must refused to open it / use it */
if (hdr_tmp.flushed_file_offset > bdrv_getlength(bs->file)) {
ret = -EINVAL;
goto exit;
}
ret = vhdx_log_read_desc(bs, s, &logs->log, &desc_entries);
if (ret < 0) {
goto exit;
}
for (i = 0; i < desc_entries->hdr.descriptor_count; i++) {
if (!memcmp(&desc_entries->desc[i].signature, "desc", 4)) {
/* data sector, so read a sector to flush */
ret = vhdx_log_read_sectors(bs, &logs->log, §ors_read,
data, 1, false);
if (ret < 0) {
goto exit;
}
if (sectors_read != 1) {
ret = -EINVAL;
goto exit;
}
}
ret = vhdx_log_flush_desc(bs, &desc_entries->desc[i], data);
if (ret < 0) {
goto exit;
}
}
if (bdrv_getlength(bs->file) < desc_entries->hdr.last_file_offset) {
new_file_size = desc_entries->hdr.last_file_offset;
if (new_file_size % (1024*1024)) {
/* round up to nearest 1MB boundary */
new_file_size = ((new_file_size >> 20) + 1) << 20;
bdrv_truncate(bs->file, new_file_size);
}
}
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;
}
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 int64_t blkverify_getlength(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
return bdrv_getlength(s->test_file);
}
static void coroutine_fn commit_run(void *opaque)
{
CommitBlockJob *s = opaque;
BlockDriverState *active = s->active;
BlockDriverState *top = s->top;
BlockDriverState *base = s->base;
BlockDriverState *overlay_bs = NULL;
int64_t sector_num, end;
int ret = 0;
int n = 0;
void *buf;
int bytes_written = 0;
int64_t base_len;
ret = s->common.len = bdrv_getlength(top);
if (s->common.len < 0) {
goto exit_restore_reopen;
}
ret = base_len = bdrv_getlength(base);
if (base_len < 0) {
goto exit_restore_reopen;
}
if (base_len < s->common.len) {
ret = bdrv_truncate(base, s->common.len);
if (ret) {
goto exit_restore_reopen;
}
}
overlay_bs = bdrv_find_overlay(active, top);
end = s->common.len >> BDRV_SECTOR_BITS;
buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);
for (sector_num = 0; sector_num < end; sector_num += n) {
uint64_t delay_ms = 0;
bool copy;
wait:
/* Note that even when no rate limit is applied we need to yield
* with no pending I/O here so that qemu_aio_flush() returns.
*/
block_job_sleep(&s->common, rt_clock, delay_ms);
if (block_job_is_cancelled(&s->common)) {
break;
}
/* Copy if allocated above the base */
ret = bdrv_co_is_allocated_above(top, base, sector_num,
COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
&n);
copy = (ret == 1);
trace_commit_one_iteration(s, sector_num, n, ret);
if (copy) {
if (s->common.speed) {
delay_ms = ratelimit_calculate_delay(&s->limit, n);
if (delay_ms > 0) {
goto wait;
}
}
ret = commit_populate(top, base, sector_num, n, buf);
bytes_written += n * BDRV_SECTOR_SIZE;
}
if (ret < 0) {
if (s->on_error == BLOCK_ERR_STOP_ANY ||
s->on_error == BLOCK_ERR_REPORT ||
(s->on_error == BLOCK_ERR_STOP_ENOSPC && ret == -ENOSPC)) {
goto exit_free_buf;
} else {
n = 0;
continue;
}
}
/* Publish progress */
s->common.offset += n * BDRV_SECTOR_SIZE;
}
ret = 0;
if (!block_job_is_cancelled(&s->common) && sector_num == end) {
/* success */
ret = bdrv_drop_intermediate(active, top, base);
}
exit_free_buf:
qemu_vfree(buf);
exit_restore_reopen:
/* restore base open flags here if appropriate (e.g., change the base back
* to r/o). These reopens do not need to be atomic, since we won't abort
* even on failure here */
if (s->base_flags != bdrv_get_flags(base)) {
bdrv_reopen(base, s->base_flags, NULL);
}
if (s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
}
block_job_complete(&s->common, ret);
}
