/**
* Update header in-place (does not rewrite backing filename or other strings)
*
* This function only updates known header fields in-place and does not affect
* extra data after the QED header.
*/
static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
void *opaque)
{
/* We must write full sectors for O_DIRECT but cannot necessarily generate
* the data following the header if an unrecognized compat feature is
* active. Therefore, first read the sectors containing the header, update
* them, and write back.
*/
int nsectors = (sizeof(QEDHeader) + BDRV_SECTOR_SIZE - 1) /
BDRV_SECTOR_SIZE;
size_t len = nsectors * BDRV_SECTOR_SIZE;
QEDWriteHeaderCB *write_header_cb = gencb_alloc(sizeof(*write_header_cb),
cb, opaque);
write_header_cb->s = s;
write_header_cb->nsectors = nsectors;
write_header_cb->buf = qemu_blockalign(s->bs, len);
write_header_cb->iov.iov_base = write_header_cb->buf;
write_header_cb->iov.iov_len = len;
qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1);
bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
qed_write_header_read_cb, write_header_cb);
}
static void *qemu_io_alloc(size_t len, int pattern)
{
void *buf;
if (misalign)
len += MISALIGN_OFFSET;
buf = qemu_blockalign(bs, len);
memset(buf, pattern, len);
if (misalign)
buf += MISALIGN_OFFSET;
return buf;
}
/* Reads the log header, and subsequent descriptors (if any). This
* will allocate all the space for buffer, which must be NULL when
* passed into this function. Each descriptor will also be validated,
* and error returned if any are invalid. */
static int vhdx_log_read_desc(BlockDriverState *bs, BDRVVHDXState *s,
VHDXLogEntries *log, VHDXLogDescEntries **buffer)
{
int ret = 0;
uint32_t desc_sectors;
uint32_t sectors_read;
VHDXLogEntryHeader hdr;
VHDXLogDescEntries *desc_entries = NULL;
int i;
assert(*buffer == NULL);
ret = vhdx_log_peek_hdr(bs, log, &hdr);
if (ret < 0) {
goto exit;
}
vhdx_log_entry_hdr_le_import(&hdr);
if (vhdx_log_hdr_is_valid(log, &hdr, s) == false) {
ret = -EINVAL;
goto exit;
}
desc_sectors = vhdx_compute_desc_sectors(hdr.descriptor_count);
desc_entries = qemu_blockalign(bs, desc_sectors * VHDX_LOG_SECTOR_SIZE);
ret = vhdx_log_read_sectors(bs, log, §ors_read, desc_entries,
desc_sectors, false);
if (ret < 0) {
goto free_and_exit;
}
if (sectors_read != desc_sectors) {
ret = -EINVAL;
goto free_and_exit;
}
/* put in proper endianness, and validate each desc */
for (i = 0; i < hdr.descriptor_count; i++) {
vhdx_log_desc_le_import(&desc_entries->desc[i]);
if (vhdx_log_desc_is_valid(&desc_entries->desc[i], &hdr) == false) {
ret = -EINVAL;
goto free_and_exit;
}
}
*buffer = desc_entries;
goto exit;
free_and_exit:
qemu_vfree(desc_entries);
exit:
return ret;
}
Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
{
BDRVQcowState *s = bs->opaque;
Qcow2Cache *c;
int i;
c = g_malloc0(sizeof(*c));
c->size = num_tables;
c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
for (i = 0; i < c->size; i++) {
c->entries[i].table = qemu_blockalign(bs, s->cluster_size);
}
return c;
}
static int raw_open_common(BlockDriverState *bs, const char *filename,
int bdrv_flags, int open_flags)
{
BDRVRawState *s = bs->opaque;
int fd, ret;
posix_aio_init();
s->lseek_err_cnt = 0;
s->open_flags = open_flags | O_BINARY;
s->open_flags &= ~O_ACCMODE;
if ((bdrv_flags & BDRV_O_ACCESS) == BDRV_O_RDWR) {
s->open_flags |= O_RDWR;
} else {
s->open_flags |= O_RDONLY;
bs->read_only = 1;
}
/* Use O_DSYNC for write-through caching, no flags for write-back caching,
* and O_DIRECT for no caching. */
if ((bdrv_flags & BDRV_O_NOCACHE))
s->open_flags |= O_DIRECT;
else if (!(bdrv_flags & BDRV_O_CACHE_WB))
s->open_flags |= O_DSYNC;
s->fd = -1;
fd = open(filename, s->open_flags, 0644);
if (fd < 0) {
ret = -errno;
if (ret == -EROFS)
ret = -EACCES;
return ret;
}
s->fd = fd;
s->aligned_buf = NULL;
if ((bdrv_flags & BDRV_O_NOCACHE)) {
s->aligned_buf = qemu_blockalign(bs, ALIGNED_BUFFER_SIZE);
if (s->aligned_buf == NULL) {
ret = -errno;
close(fd);
return ret;
}
}
return 0;
}
/**
* Write out an updated part or all of a table
*
* @s: QED state
* @offset: Offset of table in image file, in bytes
* @table: Table
* @index: Index of first element
* @n: Number of elements
* @flush: Whether or not to sync to disk
* @cb: Completion function
* @opaque: Argument for completion function
*/
static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
unsigned int index, unsigned int n, bool flush,
BlockDriverCompletionFunc *cb, void *opaque)
{
QEDWriteTableCB *write_table_cb;
BlockDriverAIOCB *aiocb;
unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1;
unsigned int start, end, i;
size_t len_bytes;
trace_qed_write_table(s, offset, table, index, n);
/* Calculate indices of the first and one after last elements */
start = index & ~sector_mask;
end = (index + n + sector_mask) & ~sector_mask;
len_bytes = (end - start) * sizeof(uint64_t);
write_table_cb = gencb_alloc(sizeof(*write_table_cb), cb, opaque);
write_table_cb->s = s;
write_table_cb->orig_table = table;
write_table_cb->flush = flush;
write_table_cb->table = qemu_blockalign(s->bs, len_bytes);
write_table_cb->iov.iov_base = write_table_cb->table->offsets;
write_table_cb->iov.iov_len = len_bytes;
qemu_iovec_init_external(&write_table_cb->qiov, &write_table_cb->iov, 1);
/* Byteswap table */
for (i = start; i < end; i++) {
uint64_t le_offset = cpu_to_le64(table->offsets[i]);
write_table_cb->table->offsets[i - start] = le_offset;
}
/* Adjust for offset into table */
offset += start * sizeof(uint64_t);
aiocb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
&write_table_cb->qiov,
write_table_cb->qiov.size / BDRV_SECTOR_SIZE,
qed_write_table_cb, write_table_cb);
if (!aiocb) {
qed_write_table_cb(write_table_cb, -EIO);
}
}
static NBDRequest *nbd_request_get(NBDClient *client)
{
NBDRequest *req;
NBDExport *exp = client->exp;
assert(client->nb_requests <= MAX_NBD_REQUESTS - 1);
client->nb_requests++;
if (QSIMPLEQ_EMPTY(&exp->requests)) {
req = g_malloc0(sizeof(NBDRequest));
req->data = qemu_blockalign(exp->bs, NBD_BUFFER_SIZE);
} else {
req = QSIMPLEQ_FIRST(&exp->requests);
QSIMPLEQ_REMOVE_HEAD(&exp->requests, entry);
}
nbd_client_get(client);
req->client = client;
return req;
}
static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
nb_sectors, cb, opaque);
acb->verify = blkverify_verify_readv;
acb->buf = qemu_blockalign(bs->file, qiov->size);
qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
blkverify_aio_cb, acb);
bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
blkverify_aio_cb, acb);
return &acb->common;
}
static int compare_full_images (void)
{
CompareFullCB *cf;
int old_copy_on_read = FALSE;
printf ("Performing a full comparison of the truth image and "
"the test image...\n");
if (!strncmp (bs->drv->format_name, "fvd", 3)) {
/* Disable copy-on-read when scanning through the entire image. */
old_copy_on_read = fvd_get_copy_on_read (bs);
fvd_set_copy_on_read (bs, FALSE);
}
cf = g_malloc(sizeof(CompareFullCB));
cf->max_nb_sectors = 1048576L / 512;
cf->nb_sectors = MIN (cf->max_nb_sectors, total_sectors);
if (posix_memalign ((void **) &cf->truth_buf, 512,
cf->max_nb_sectors * 512) != 0) {
die ("posix_memalign");
}
cf->iov.iov_base = qemu_blockalign (bs, cf->max_nb_sectors * 512);
cf->iov.iov_len = cf->nb_sectors * 512;
cf->sector_num = 0;
qemu_iovec_init_external (&cf->qiov, &cf->iov, 1);
if (!bdrv_aio_readv (bs, cf->sector_num, &cf->qiov,
cf->nb_sectors, compare_full_images_cb, cf)) {
die ("bdrv_aio_readv\n");
}
sim_all_tasks ();
if (!strncmp (bs->drv->format_name, "fvd", 3)) {
fvd_set_copy_on_read (bs, old_copy_on_read);
}
return 0;
}
QEDTable *qed_alloc_table(BDRVQEDState *s)
{
/* Honor O_DIRECT memory alignment requirements */
return qemu_blockalign(s->bs,
s->header.cluster_size * s->header.table_size);
}
int main(int argc, char **argv)
{
BlockDriverState *bs;
off_t dev_offset = 0;
off_t offset = 0;
bool readonly = false;
bool disconnect = false;
const char *bindto = "0.0.0.0";
int port = NBD_DEFAULT_PORT;
struct sockaddr_in addr;
socklen_t addr_len = sizeof(addr);
off_t fd_size;
char *device = NULL;
char *socket = NULL;
char sockpath[128];
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:t";
struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "bind", 1, NULL, 'b' },
{ "port", 1, NULL, 'p' },
{ "socket", 1, NULL, 'k' },
{ "offset", 1, NULL, 'o' },
{ "read-only", 0, NULL, 'r' },
{ "partition", 1, NULL, 'P' },
{ "connect", 1, NULL, 'c' },
{ "disconnect", 0, NULL, 'd' },
{ "snapshot", 0, NULL, 's' },
{ "nocache", 0, NULL, 'n' },
{ "shared", 1, NULL, 'e' },
{ "persistent", 0, NULL, 't' },
{ "verbose", 0, NULL, 'v' },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
int li;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret;
int shared = 1;
uint8_t *data;
fd_set fds;
int *sharing_fds;
int fd;
int i;
int nb_fds = 0;
int max_fd;
int persistent = 0;
uint32_t nbdflags;
while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) {
switch (ch) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
flags |= BDRV_O_NOCACHE;
break;
case 'b':
bindto = optarg;
break;
case 'p':
li = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid port `%s'", optarg);
}
if (li < 1 || li > 65535) {
errx(EXIT_FAILURE, "Port out of range `%s'", optarg);
}
port = (uint16_t)li;
break;
case 'o':
dev_offset = strtoll (optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid offset `%s'", optarg);
}
if (dev_offset < 0) {
errx(EXIT_FAILURE, "Offset must be positive `%s'", optarg);
}
break;
case 'r':
readonly = true;
flags &= ~BDRV_O_RDWR;
break;
case 'P':
partition = strtol(optarg, &end, 0);
if (*end)
errx(EXIT_FAILURE, "Invalid partition `%s'", optarg);
if (partition < 1 || partition > 8)
errx(EXIT_FAILURE, "Invalid partition %d", partition);
break;
case 'k':
socket = optarg;
if (socket[0] != '/')
errx(EXIT_FAILURE, "socket path must be absolute\n");
break;
case 'd':
disconnect = true;
break;
case 'c':
device = optarg;
break;
case 'e':
shared = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid shared device number '%s'", optarg);
}
if (shared < 1) {
errx(EXIT_FAILURE, "Shared device number must be greater than 0\n");
}
break;
case 't':
persistent = 1;
break;
case 'v':
verbose = 1;
break;
case 'V':
version(argv[0]);
exit(0);
break;
case 'h':
usage(argv[0]);
exit(0);
break;
case '?':
errx(EXIT_FAILURE, "Try `%s --help' for more information.",
argv[0]);
}
}
if ((argc - optind) != 1) {
errx(EXIT_FAILURE, "Invalid number of argument.\n"
"Try `%s --help' for more information.",
argv[0]);
}
if (disconnect) {
fd = open(argv[optind], O_RDWR);
if (fd == -1)
err(EXIT_FAILURE, "Cannot open %s", argv[optind]);
nbd_disconnect(fd);
close(fd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
bdrv_init();
bs = bdrv_new("hda");
if (bs == NULL)
return 1;
if ((ret = bdrv_open(bs, argv[optind], flags, NULL)) < 0) {
errno = -ret;
err(EXIT_FAILURE, "Failed to bdrv_open '%s'", argv[optind]);
}
fd_size = bs->total_sectors * 512;
if (partition != -1 &&
find_partition(bs, partition, &dev_offset, &fd_size))
err(EXIT_FAILURE, "Could not find partition %d", partition);
if (device) {
pid_t pid;
int sock;
/* want to fail before daemonizing */
if (access(device, R_OK|W_OK) == -1) {
err(EXIT_FAILURE, "Could not access '%s'", device);
}
if (!verbose) {
/* detach client and server */
if (daemon(0, 0) == -1) {
err(EXIT_FAILURE, "Failed to daemonize");
}
}
if (socket == NULL) {
snprintf(sockpath, sizeof(sockpath), SOCKET_PATH,
basename(device));
socket = sockpath;
}
pid = fork();
if (pid < 0)
return 1;
if (pid != 0) {
off_t size;
size_t blocksize;
ret = 0;
bdrv_close(bs);
do {
sock = unix_socket_outgoing(socket);
if (sock == -1) {
if (errno != ENOENT && errno != ECONNREFUSED) {
ret = 1;
goto out;
}
sleep(1); /* wait children */
}
} while (sock == -1);
fd = open(device, O_RDWR);
if (fd == -1) {
ret = 1;
goto out;
}
ret = nbd_receive_negotiate(sock, NULL, &nbdflags,
&size, &blocksize);
if (ret == -1) {
ret = 1;
goto out;
}
ret = nbd_init(fd, sock, size, blocksize);
if (ret == -1) {
ret = 1;
goto out;
}
printf("NBD device %s is now connected to file %s\n",
device, argv[optind]);
/* update partition table */
show_parts(device);
ret = nbd_client(fd);
if (ret) {
ret = 1;
}
close(fd);
out:
kill(pid, SIGTERM);
unlink(socket);
return ret;
}
/* children */
}
sharing_fds = qemu_malloc((shared + 1) * sizeof(int));
if (socket) {
sharing_fds[0] = unix_socket_incoming(socket);
} else {
sharing_fds[0] = tcp_socket_incoming(bindto, port);
}
if (sharing_fds[0] == -1)
return 1;
max_fd = sharing_fds[0];
nb_fds++;
data = qemu_blockalign(bs, NBD_BUFFER_SIZE);
if (data == NULL)
errx(EXIT_FAILURE, "Cannot allocate data buffer");
do {
FD_ZERO(&fds);
for (i = 0; i < nb_fds; i++)
FD_SET(sharing_fds[i], &fds);
ret = select(max_fd + 1, &fds, NULL, NULL, NULL);
if (ret == -1)
break;
if (FD_ISSET(sharing_fds[0], &fds))
ret--;
for (i = 1; i < nb_fds && ret; i++) {
if (FD_ISSET(sharing_fds[i], &fds)) {
if (nbd_trip(bs, sharing_fds[i], fd_size, dev_offset,
&offset, readonly, data, NBD_BUFFER_SIZE) != 0) {
close(sharing_fds[i]);
nb_fds--;
sharing_fds[i] = sharing_fds[nb_fds];
i--;
}
ret--;
}
}
/* new connection ? */
if (FD_ISSET(sharing_fds[0], &fds)) {
if (nb_fds < shared + 1) {
sharing_fds[nb_fds] = accept(sharing_fds[0],
(struct sockaddr *)&addr,
&addr_len);
if (sharing_fds[nb_fds] != -1 &&
nbd_negotiate(sharing_fds[nb_fds], fd_size) != -1) {
if (sharing_fds[nb_fds] > max_fd)
max_fd = sharing_fds[nb_fds];
nb_fds++;
}
}
}
} while (persistent || nb_fds > 1);
qemu_vfree(data);
close(sharing_fds[0]);
bdrv_close(bs);
qemu_free(sharing_fds);
if (socket)
unlink(socket);
return 0;
}
static 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);
}
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;
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);
}
/* Flushes the descriptor described by desc to the VHDX image file.
* If the descriptor is a data descriptor, than 'data' must be non-NULL,
* and >= 4096 bytes (VHDX_LOG_SECTOR_SIZE), containing the data to be
* written.
*
* Verification is performed to make sure the sequence numbers of a data
* descriptor match the sequence number in the desc.
*
* For a zero descriptor, it may describe multiple sectors to fill with zeroes.
* In this case, it should be noted that zeroes are written to disk, and the
* image file is not extended as a sparse file. */
static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc,
VHDXLogDataSector *data)
{
int ret = 0;
uint64_t seq, file_offset;
uint32_t offset = 0;
void *buffer = NULL;
uint64_t count = 1;
int i;
buffer = qemu_blockalign(bs, VHDX_LOG_SECTOR_SIZE);
if (!memcmp(&desc->signature, "desc", 4)) {
/* data sector */
if (data == NULL) {
ret = -EFAULT;
goto exit;
}
/* The sequence number of the data sector must match that
* in the descriptor */
seq = data->sequence_high;
seq <<= 32;
seq |= data->sequence_low & 0xffffffff;
if (seq != desc->sequence_number) {
ret = -EINVAL;
goto exit;
}
/* Each data sector is in total 4096 bytes, however the first
* 8 bytes, and last 4 bytes, are located in the descriptor */
memcpy(buffer, &desc->leading_bytes, 8);
offset += 8;
memcpy(buffer+offset, data->data, 4084);
offset += 4084;
memcpy(buffer+offset, &desc->trailing_bytes, 4);
} else if (!memcmp(&desc->signature, "zero", 4)) {
/* write 'count' sectors of sector */
memset(buffer, 0, VHDX_LOG_SECTOR_SIZE);
count = desc->zero_length / VHDX_LOG_SECTOR_SIZE;
}
file_offset = desc->file_offset;
/* count is only > 1 if we are writing zeroes */
for (i = 0; i < count; i++) {
ret = bdrv_pwrite_sync(bs->file, file_offset, buffer,
VHDX_LOG_SECTOR_SIZE);
if (ret < 0) {
goto exit;
}
file_offset += VHDX_LOG_SECTOR_SIZE;
}
exit:
qemu_vfree(buffer);
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 ssize_t handle_aiocb_rw(RawPosixAIOData *aiocb)
{
ssize_t nbytes;
char *buf;
if (!(aiocb->aio_type & QEMU_AIO_MISALIGNED)) {
/*
* If there is just a single buffer, and it is properly aligned
* we can just use plain pread/pwrite without any problems.
*/
if (aiocb->aio_niov == 1) {
return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);
}
/*
* We have more than one iovec, and all are properly aligned.
*
* Try preadv/pwritev first and fall back to linearizing the
* buffer if it's not supported.
*/
if (preadv_present) {
nbytes = handle_aiocb_rw_vector(aiocb);
if (nbytes == aiocb->aio_nbytes ||
(nbytes < 0 && nbytes != -ENOSYS)) {
return nbytes;
}
preadv_present = false;
}
/*
* XXX(hch): short read/write. no easy way to handle the reminder
* using these interfaces. For now retry using plain
* pread/pwrite?
*/
}
/*
* Ok, we have to do it the hard way, copy all segments into
* a single aligned buffer.
*/
buf = qemu_blockalign(aiocb->bs, aiocb->aio_nbytes);
if (aiocb->aio_type & QEMU_AIO_WRITE) {
char *p = buf;
int i;
for (i = 0; i < aiocb->aio_niov; ++i) {
memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
p += aiocb->aio_iov[i].iov_len;
}
}
nbytes = handle_aiocb_rw_linear(aiocb, buf);
if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
char *p = buf;
size_t count = aiocb->aio_nbytes, copy;
int i;
for (i = 0; i < aiocb->aio_niov && count; ++i) {
copy = count;
if (copy > aiocb->aio_iov[i].iov_len) {
copy = aiocb->aio_iov[i].iov_len;
}
memcpy(aiocb->aio_iov[i].iov_base, p, copy);
p += copy;
count -= copy;
}
}
qemu_vfree(buf);
return nbytes;
}
static BlockDriverAIOCB *rbd_aio_rw_vector(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque, int write)
{
RBDAIOCB *acb;
RADOSCB *rcb;
rbd_completion_t c;
int64_t off, size;
char *buf;
int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque);
if (!acb) {
return NULL;
}
acb->write = write;
acb->qiov = qiov;
acb->bounce = qemu_blockalign(bs, qiov->size);
acb->ret = 0;
acb->error = 0;
acb->s = s;
acb->cancelled = 0;
acb->bh = NULL;
if (write) {
qemu_iovec_to_buffer(acb->qiov, acb->bounce);
}
buf = acb->bounce;
off = sector_num * BDRV_SECTOR_SIZE;
size = nb_sectors * BDRV_SECTOR_SIZE;
s->qemu_aio_count++; /* All the RADOSCB */
rcb = g_malloc(sizeof(RADOSCB));
rcb->done = 0;
rcb->acb = acb;
rcb->buf = buf;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
if (r < 0) {
goto failed;
}
if (write) {
r = rbd_aio_write(s->image, off, size, buf, c);
} else {
r = rbd_aio_read(s->image, off, size, buf, c);
}
if (r < 0) {
goto failed;
}
return &acb->common;
failed:
g_free(rcb);
s->qemu_aio_count--;
qemu_aio_release(acb);
return NULL;
}
static int raw_open_common(BlockDriverState *bs, const char *filename,
int bdrv_flags, int open_flags)
{
BDRVRawState *s = bs->opaque;
int fd, ret;
s->open_flags = open_flags | O_BINARY;
s->open_flags &= ~O_ACCMODE;
if (bdrv_flags & BDRV_O_RDWR) {
s->open_flags |= O_RDWR;
} else {
s->open_flags |= O_RDONLY;
}
/* Use O_DSYNC for write-through caching, no flags for write-back caching,
* and O_DIRECT for no caching. */
if ((bdrv_flags & BDRV_O_NOCACHE))
s->open_flags |= O_DIRECT;
else if (!(bdrv_flags & BDRV_O_CACHE_WB))
s->open_flags |= O_DSYNC;
s->fd = -1;
fd = qemu_open(filename, s->open_flags, 0644);
if (fd < 0) {
ret = -errno;
if (ret == -EROFS)
ret = -EACCES;
return ret;
}
s->fd = fd;
s->aligned_buf = NULL;
if ((bdrv_flags & BDRV_O_NOCACHE)) {
s->aligned_buf = qemu_blockalign(bs, ALIGNED_BUFFER_SIZE);
if (s->aligned_buf == NULL) {
goto out_close;
}
}
#ifdef CONFIG_LINUX_AIO
if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
(BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
/* We're falling back to POSIX AIO in some cases */
paio_init();
s->aio_ctx = laio_init();
if (!s->aio_ctx) {
goto out_free_buf;
}
s->use_aio = 1;
} else
#endif
{
if (paio_init() < 0) {
goto out_free_buf;
}
#ifdef CONFIG_LINUX_AIO
s->use_aio = 0;
#endif
}
return 0;
out_free_buf:
qemu_vfree(s->aligned_buf);
out_close:
close(fd);
return -errno;
}
/* opens the specified header block from the VHDX file header section */
static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
{
int ret = 0;
VHDXHeader *header1;
VHDXHeader *header2;
bool h1_valid = false;
bool h2_valid = false;
uint64_t h1_seq = 0;
uint64_t h2_seq = 0;
uint8_t *buffer;
header1 = qemu_blockalign(bs, sizeof(VHDXHeader));
header2 = qemu_blockalign(bs, sizeof(VHDXHeader));
buffer = qemu_blockalign(bs, VHDX_HEADER_SIZE);
s->headers[0] = header1;
s->headers[1] = header2;
/* We have to read the whole VHDX_HEADER_SIZE instead of
* sizeof(VHDXHeader), because the checksum is over the whole
* region */
ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE);
if (ret < 0) {
goto fail;
}
/* copy over just the relevant portion that we need */
memcpy(header1, buffer, sizeof(VHDXHeader));
vhdx_header_le_import(header1);
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
!memcmp(&header1->signature, "head", 4) &&
header1->version == 1) {
h1_seq = header1->sequence_number;
h1_valid = true;
}
ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE);
if (ret < 0) {
goto fail;
}
/* copy over just the relevant portion that we need */
memcpy(header2, buffer, sizeof(VHDXHeader));
vhdx_header_le_import(header2);
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
!memcmp(&header2->signature, "head", 4) &&
header2->version == 1) {
h2_seq = header2->sequence_number;
h2_valid = true;
}
/* If there is only 1 valid header (or no valid headers), we
* don't care what the sequence numbers are */
if (h1_valid && !h2_valid) {
s->curr_header = 0;
} else if (!h1_valid && h2_valid) {
s->curr_header = 1;
} else if (!h1_valid && !h2_valid) {
ret = -EINVAL;
goto fail;
} else {
/* If both headers are valid, then we choose the active one by the
* highest sequence number. If the sequence numbers are equal, that is
* invalid */
if (h1_seq > h2_seq) {
s->curr_header = 0;
} else if (h2_seq > h1_seq) {
s->curr_header = 1;
} else {
ret = -EINVAL;
goto fail;
}
}
ret = 0;
goto exit;
fail:
qerror_report(ERROR_CLASS_GENERIC_ERROR, "No valid VHDX header found");
qemu_vfree(header1);
qemu_vfree(header2);
s->headers[0] = NULL;
s->headers[1] = NULL;
exit:
qemu_vfree(buffer);
return ret;
}
int main(int argc, char **argv)
{
BlockDriverState *bs;
off_t dev_offset = 0;
off_t offset = 0;
uint32_t nbdflags = 0;
bool disconnect = false;
const char *bindto = "0.0.0.0";
int port = NBD_DEFAULT_PORT;
struct sockaddr_in addr;
socklen_t addr_len = sizeof(addr);
off_t fd_size;
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:t";
struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "bind", 1, NULL, 'b' },
{ "port", 1, NULL, 'p' },
{ "socket", 1, NULL, 'k' },
{ "offset", 1, NULL, 'o' },
{ "read-only", 0, NULL, 'r' },
{ "partition", 1, NULL, 'P' },
{ "connect", 1, NULL, 'c' },
{ "disconnect", 0, NULL, 'd' },
{ "snapshot", 0, NULL, 's' },
{ "nocache", 0, NULL, 'n' },
{ "shared", 1, NULL, 'e' },
{ "persistent", 0, NULL, 't' },
{ "verbose", 0, NULL, 'v' },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
int li;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret;
int shared = 1;
uint8_t *data;
fd_set fds;
int *sharing_fds;
int fd;
int i;
int nb_fds = 0;
int max_fd;
int persistent = 0;
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;
int sigterm_fd[2];
if (qemu_pipe(sigterm_fd) == -1) {
err(EXIT_FAILURE, "Error setting up communication pipe");
}
sigterm_wfd = sigterm_fd[1];
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]);
}
if (disconnect) {
fd = open(argv[optind], O_RDWR);
if (fd == -1)
err(EXIT_FAILURE, "Cannot open %s", argv[optind]);
nbd_disconnect(fd);
close(fd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
if (device && !verbose) {
int stderr_fd[2];
pid_t pid;
int ret;
if (qemu_pipe(stderr_fd) == -1) {
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(0, 0);
/* Temporarily redirect stderr to the parent's pipe... */
dup2(stderr_fd[1], STDERR_FILENO);
if (ret == -1) {
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 == -1) {
exit(EXIT_FAILURE);
}
}
if (ret == -1) {
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) {
/* Open before spawning new threads. In the future, we may
* drop privileges after opening.
*/
fd = open(device, O_RDWR);
if (fd == -1) {
err(EXIT_FAILURE, "Failed to open %s", device);
}
if (sockpath == NULL) {
sockpath = g_malloc(128);
snprintf(sockpath, 128, SOCKET_PATH, basename(device));
}
}
bdrv_init();
atexit(bdrv_close_all);
bs = bdrv_new("hda");
srcpath = argv[optind];
if ((ret = bdrv_open(bs, srcpath, flags, NULL)) < 0) {
errno = -ret;
err(EXIT_FAILURE, "Failed to bdrv_open '%s'", argv[optind]);
}
fd_size = bs->total_sectors * 512;
if (partition != -1 &&
find_partition(bs, partition, &dev_offset, &fd_size)) {
err(EXIT_FAILURE, "Could not find partition %d", partition);
}
sharing_fds = g_malloc((shared + 1) * sizeof(int));
if (sockpath) {
sharing_fds[0] = unix_socket_incoming(sockpath);
} else {
sharing_fds[0] = tcp_socket_incoming(bindto, port);
}
if (sharing_fds[0] == -1)
return 1;
if (device) {
int ret;
ret = pthread_create(&client_thread, NULL, nbd_client_thread, &fd);
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));
}
max_fd = sharing_fds[0];
nb_fds++;
data = qemu_blockalign(bs, NBD_BUFFER_SIZE);
if (data == NULL) {
errx(EXIT_FAILURE, "Cannot allocate data buffer");
}
do {
FD_ZERO(&fds);
FD_SET(sigterm_fd[0], &fds);
for (i = 0; i < nb_fds; i++)
FD_SET(sharing_fds[i], &fds);
do {
ret = select(max_fd + 1, &fds, NULL, NULL, NULL);
} while (ret == -1 && errno == EINTR);
if (ret == -1 || FD_ISSET(sigterm_fd[0], &fds)) {
break;
}
if (FD_ISSET(sharing_fds[0], &fds))
ret--;
for (i = 1; i < nb_fds && ret; i++) {
if (FD_ISSET(sharing_fds[i], &fds)) {
if (nbd_trip(bs, sharing_fds[i], fd_size, dev_offset,
&offset, nbdflags, data, NBD_BUFFER_SIZE) != 0) {
close(sharing_fds[i]);
nb_fds--;
sharing_fds[i] = sharing_fds[nb_fds];
i--;
}
ret--;
}
}
/* new connection ? */
if (FD_ISSET(sharing_fds[0], &fds)) {
if (nb_fds < shared + 1) {
sharing_fds[nb_fds] = accept(sharing_fds[0],
(struct sockaddr *)&addr,
&addr_len);
if (sharing_fds[nb_fds] != -1 &&
nbd_negotiate(sharing_fds[nb_fds], fd_size, nbdflags) != -1) {
if (sharing_fds[nb_fds] > max_fd)
max_fd = sharing_fds[nb_fds];
nb_fds++;
}
}
}
} while (persistent || nb_fds > 1);
qemu_vfree(data);
close(sharing_fds[0]);
g_free(sharing_fds);
if (sockpath) {
unlink(sockpath);
}
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
{
RBDAIOCB *acb;
RADOSCB *rcb;
rbd_completion_t c;
int64_t off, size;
char *buf;
int r;
BDRVRBDState *s = bs->opaque;
acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
acb->cmd = cmd;
acb->qiov = qiov;
if (cmd == RBD_AIO_DISCARD) {
acb->bounce = NULL;
} else {
acb->bounce = qemu_blockalign(bs, qiov->size);
}
acb->ret = 0;
acb->error = 0;
acb->s = s;
acb->cancelled = 0;
acb->bh = NULL;
if (cmd == RBD_AIO_WRITE) {
qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
buf = acb->bounce;
off = sector_num * BDRV_SECTOR_SIZE;
size = nb_sectors * BDRV_SECTOR_SIZE;
s->qemu_aio_count++; /* All the RADOSCB */
rcb = g_malloc(sizeof(RADOSCB));
rcb->done = 0;
rcb->acb = acb;
rcb->buf = buf;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
if (r < 0) {
goto failed;
}
switch (cmd) {
case RBD_AIO_WRITE:
r = rbd_aio_write(s->image, off, size, buf, c);
break;
case RBD_AIO_READ:
r = rbd_aio_read(s->image, off, size, buf, c);
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
break;
default:
r = -EINVAL;
}
if (r < 0) {
goto failed;
}
return &acb->common;
failed:
g_free(rcb);
s->qemu_aio_count--;
qemu_aio_release(acb);
return NULL;
}
static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
{
int ret = 0;
uint8_t *buffer;
int offset = 0;
VHDXRegionTableEntry rt_entry;
uint32_t i;
bool bat_rt_found = false;
bool metadata_rt_found = false;
/* We have to read the whole 64KB block, because the crc32 is over the
* whole block */
buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE);
ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer,
VHDX_HEADER_BLOCK_SIZE);
if (ret < 0) {
goto fail;
}
memcpy(&s->rt, buffer, sizeof(s->rt));
le32_to_cpus(&s->rt.signature);
le32_to_cpus(&s->rt.checksum);
le32_to_cpus(&s->rt.entry_count);
le32_to_cpus(&s->rt.reserved);
offset += sizeof(s->rt);
if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4) ||
memcmp(&s->rt.signature, "regi", 4)) {
ret = -EINVAL;
goto fail;
}
/* Per spec, maximum region table entry count is 2047 */
if (s->rt.entry_count > 2047) {
ret = -EINVAL;
goto fail;
}
for (i = 0; i < s->rt.entry_count; i++) {
memcpy(&rt_entry, buffer + offset, sizeof(rt_entry));
offset += sizeof(rt_entry);
leguid_to_cpus(&rt_entry.guid);
le64_to_cpus(&rt_entry.file_offset);
le32_to_cpus(&rt_entry.length);
le32_to_cpus(&rt_entry.data_bits);
/* see if we recognize the entry */
if (guid_eq(rt_entry.guid, bat_guid)) {
/* must be unique; if we have already found it this is invalid */
if (bat_rt_found) {
ret = -EINVAL;
goto fail;
}
bat_rt_found = true;
s->bat_rt = rt_entry;
continue;
}
if (guid_eq(rt_entry.guid, metadata_guid)) {
/* must be unique; if we have already found it this is invalid */
if (metadata_rt_found) {
ret = -EINVAL;
goto fail;
}
metadata_rt_found = true;
s->metadata_rt = rt_entry;
continue;
}
if (rt_entry.data_bits & VHDX_REGION_ENTRY_REQUIRED) {
/* cannot read vhdx file - required region table entry that
* we do not understand. per spec, we must fail to open */
ret = -ENOTSUP;
goto fail;
}
}
ret = 0;
fail:
qemu_vfree(buffer);
return ret;
}
static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVVHDXState *s = bs->opaque;
int ret = 0;
uint32_t i;
uint64_t signature;
uint32_t data_blocks_cnt, bitmap_blocks_cnt;
s->bat = NULL;
qemu_co_mutex_init(&s->lock);
/* validate the file signature */
ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t));
if (ret < 0) {
goto fail;
}
if (memcmp(&signature, "vhdxfile", 8)) {
ret = -EINVAL;
goto fail;
}
ret = vhdx_parse_header(bs, s);
if (ret) {
goto fail;
}
ret = vhdx_parse_log(bs, s);
if (ret) {
goto fail;
}
ret = vhdx_open_region_tables(bs, s);
if (ret) {
goto fail;
}
ret = vhdx_parse_metadata(bs, s);
if (ret) {
goto fail;
}
s->block_size = s->params.block_size;
/* the VHDX spec dictates that virtual_disk_size is always a multiple of
* logical_sector_size */
bs->total_sectors = s->virtual_disk_size >> s->logical_sector_size_bits;
data_blocks_cnt = s->virtual_disk_size >> s->block_size_bits;
if (s->virtual_disk_size - (data_blocks_cnt << s->block_size_bits)) {
data_blocks_cnt++;
}
bitmap_blocks_cnt = data_blocks_cnt >> s->chunk_ratio_bits;
if (data_blocks_cnt - (bitmap_blocks_cnt << s->chunk_ratio_bits)) {
bitmap_blocks_cnt++;
}
if (s->parent_entries) {
s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);
} else {
s->bat_entries = data_blocks_cnt +
((data_blocks_cnt - 1) >> s->chunk_ratio_bits);
}
s->bat_offset = s->bat_rt.file_offset;
if (s->bat_entries > s->bat_rt.length / sizeof(VHDXBatEntry)) {
/* BAT allocation is not large enough for all entries */
ret = -EINVAL;
goto fail;
}
s->bat = qemu_blockalign(bs, s->bat_rt.length);
ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
if (ret < 0) {
goto fail;
}
for (i = 0; i < s->bat_entries; i++) {
le64_to_cpus(&s->bat[i]);
}
if (flags & BDRV_O_RDWR) {
ret = -ENOTSUP;
goto fail;
}
/* TODO: differencing files, write */
/* Disable migration when VHDX images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vhdx", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
return 0;
fail:
qemu_vfree(s->headers[0]);
qemu_vfree(s->headers[1]);
qemu_vfree(s->bat);
qemu_vfree(s->parent_entries);
return ret;
}
/* Metadata initial parser
*
* This loads all the metadata entry fields. This may cause additional
* fields to be processed (e.g. parent locator, etc..).
*
* There are 5 Metadata items that are always required:
* - File Parameters (block size, has a parent)
* - Virtual Disk Size (size, in bytes, of the virtual drive)
* - Page 83 Data (scsi page 83 guid)
* - Logical Sector Size (logical sector size in bytes, either 512 or
* 4096. We only support 512 currently)
* - Physical Sector Size (512 or 4096)
*
* Also, if the File Parameters indicate this is a differencing file,
* we must also look for the Parent Locator metadata item.
*/
static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
{
int ret = 0;
uint8_t *buffer;
int offset = 0;
uint32_t i = 0;
VHDXMetadataTableEntry md_entry;
buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE);
ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer,
VHDX_METADATA_TABLE_MAX_SIZE);
if (ret < 0) {
goto exit;
}
memcpy(&s->metadata_hdr, buffer, sizeof(s->metadata_hdr));
offset += sizeof(s->metadata_hdr);
le64_to_cpus(&s->metadata_hdr.signature);
le16_to_cpus(&s->metadata_hdr.reserved);
le16_to_cpus(&s->metadata_hdr.entry_count);
if (memcmp(&s->metadata_hdr.signature, "metadata", 8)) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.present = 0;
if ((s->metadata_hdr.entry_count * sizeof(md_entry)) >
(VHDX_METADATA_TABLE_MAX_SIZE - offset)) {
ret = -EINVAL;
goto exit;
}
for (i = 0; i < s->metadata_hdr.entry_count; i++) {
memcpy(&md_entry, buffer + offset, sizeof(md_entry));
offset += sizeof(md_entry);
leguid_to_cpus(&md_entry.item_id);
le32_to_cpus(&md_entry.offset);
le32_to_cpus(&md_entry.length);
le32_to_cpus(&md_entry.data_bits);
le32_to_cpus(&md_entry.reserved2);
if (guid_eq(md_entry.item_id, file_param_guid)) {
if (s->metadata_entries.present & META_FILE_PARAMETER_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.file_parameters_entry = md_entry;
s->metadata_entries.present |= META_FILE_PARAMETER_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, virtual_size_guid)) {
if (s->metadata_entries.present & META_VIRTUAL_DISK_SIZE_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.virtual_disk_size_entry = md_entry;
s->metadata_entries.present |= META_VIRTUAL_DISK_SIZE_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, page83_guid)) {
if (s->metadata_entries.present & META_PAGE_83_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.page83_data_entry = md_entry;
s->metadata_entries.present |= META_PAGE_83_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, logical_sector_guid)) {
if (s->metadata_entries.present &
META_LOGICAL_SECTOR_SIZE_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.logical_sector_size_entry = md_entry;
s->metadata_entries.present |= META_LOGICAL_SECTOR_SIZE_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, phys_sector_guid)) {
if (s->metadata_entries.present & META_PHYS_SECTOR_SIZE_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.phys_sector_size_entry = md_entry;
s->metadata_entries.present |= META_PHYS_SECTOR_SIZE_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, parent_locator_guid)) {
if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.parent_locator_entry = md_entry;
s->metadata_entries.present |= META_PARENT_LOCATOR_PRESENT;
continue;
}
if (md_entry.data_bits & VHDX_META_FLAGS_IS_REQUIRED) {
/* cannot read vhdx file - required region table entry that
* we do not understand. per spec, we must fail to open */
ret = -ENOTSUP;
goto exit;
}
}
if (s->metadata_entries.present != META_ALL_PRESENT) {
ret = -ENOTSUP;
goto exit;
}
ret = bdrv_pread(bs->file,
s->metadata_entries.file_parameters_entry.offset
+ s->metadata_rt.file_offset,
&s->params,
sizeof(s->params));
if (ret < 0) {
goto exit;
}
le32_to_cpus(&s->params.block_size);
le32_to_cpus(&s->params.data_bits);
/* We now have the file parameters, so we can tell if this is a
* differencing file (i.e.. has_parent), is dynamic or fixed
* sized (leave_blocks_allocated), and the block size */
/* The parent locator required iff the file parameters has_parent set */
if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
/* TODO: parse parent locator fields */
ret = -ENOTSUP; /* temp, until differencing files are supported */
goto exit;
} else {
/* if has_parent is set, but there is not parent locator present,
* then that is an invalid combination */
ret = -EINVAL;
goto exit;
}
}
/* determine virtual disk size, logical sector size,
* and phys sector size */
ret = bdrv_pread(bs->file,
s->metadata_entries.virtual_disk_size_entry.offset
+ s->metadata_rt.file_offset,
&s->virtual_disk_size,
sizeof(uint64_t));
if (ret < 0) {
goto exit;
}
ret = bdrv_pread(bs->file,
s->metadata_entries.logical_sector_size_entry.offset
+ s->metadata_rt.file_offset,
&s->logical_sector_size,
sizeof(uint32_t));
if (ret < 0) {
goto exit;
}
ret = bdrv_pread(bs->file,
s->metadata_entries.phys_sector_size_entry.offset
+ s->metadata_rt.file_offset,
&s->physical_sector_size,
sizeof(uint32_t));
if (ret < 0) {
goto exit;
}
le64_to_cpus(&s->virtual_disk_size);
le32_to_cpus(&s->logical_sector_size);
le32_to_cpus(&s->physical_sector_size);
if (s->logical_sector_size == 0 || s->params.block_size == 0) {
ret = -EINVAL;
goto exit;
}
/* both block_size and sector_size are guaranteed powers of 2 */
s->sectors_per_block = s->params.block_size / s->logical_sector_size;
s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
(uint64_t)s->logical_sector_size /
(uint64_t)s->params.block_size;
/* These values are ones we will want to use for division / multiplication
* later on, and they are all guaranteed (per the spec) to be powers of 2,
* so we can take advantage of that for shift operations during
* reads/writes */
if (s->logical_sector_size & (s->logical_sector_size - 1)) {
ret = -EINVAL;
goto exit;
}
if (s->sectors_per_block & (s->sectors_per_block - 1)) {
ret = -EINVAL;
goto exit;
}
if (s->chunk_ratio & (s->chunk_ratio - 1)) {
ret = -EINVAL;
goto exit;
}
s->block_size = s->params.block_size;
if (s->block_size & (s->block_size - 1)) {
ret = -EINVAL;
goto exit;
}
s->logical_sector_size_bits = 31 - clz32(s->logical_sector_size);
s->sectors_per_block_bits = 31 - clz32(s->sectors_per_block);
s->chunk_ratio_bits = 63 - clz64(s->chunk_ratio);
s->block_size_bits = 31 - clz32(s->block_size);
ret = 0;
exit:
qemu_vfree(buffer);
return ret;
}
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 int img_convert(int argc, char **argv)
{
int c, ret = 0, n, n1, bs_n, bs_i, compress, cluster_size, cluster_sectors;
int progress = 0, flags;
const char *fmt, *out_fmt, *cache, *out_baseimg, *out_filename;
BlockDriver *drv, *proto_drv;
BlockDriverState **bs = NULL, *out_bs = NULL;
int64_t total_sectors, nb_sectors, sector_num, bs_offset;
uint64_t bs_sectors;
uint8_t * buf = NULL;
const uint8_t *buf1;
BlockDriverInfo bdi;
QEMUOptionParameter *param = NULL, *create_options = NULL;
QEMUOptionParameter *out_baseimg_param;
char *options = NULL;
const char *snapshot_name = NULL;
float local_progress;
int min_sparse = 8; /* Need at least 4k of zeros for sparse detection */
fmt = NULL;
out_fmt = "raw";
cache = "unsafe";
out_baseimg = NULL;
compress = 0;
for(;;) {
c = getopt(argc, argv, "f:O:B:s:hce6o:pS:t:");
if (c == -1) {
break;
}
switch(c) {
case '?':
case 'h':
help();
break;
case 'f':
fmt = optarg;
break;
case 'O':
out_fmt = optarg;
break;
case 'B':
out_baseimg = optarg;
break;
case 'c':
compress = 1;
break;
case 'e':
error_report("option -e is deprecated, please use \'-o "
"encryption\' instead!");
return 1;
case '6':
error_report("option -6 is deprecated, please use \'-o "
"compat6\' instead!");
return 1;
case 'o':
options = optarg;
break;
case 's':
snapshot_name = optarg;
break;
case 'S':
{
int64_t sval;
char *end;
sval = strtosz_suffix(optarg, &end, STRTOSZ_DEFSUFFIX_B);
if (sval < 0 || *end) {
error_report("Invalid minimum zero buffer size for sparse output specified");
return 1;
}
min_sparse = sval / BDRV_SECTOR_SIZE;
break;
}
case 'p':
progress = 1;
break;
case 't':
cache = optarg;
break;
}
}
bs_n = argc - optind - 1;
if (bs_n < 1) {
help();
}
out_filename = argv[argc - 1];
if (options && !strcmp(options, "?")) {
ret = print_block_option_help(out_filename, out_fmt);
goto out;
}
if (bs_n > 1 && out_baseimg) {
error_report("-B makes no sense when concatenating multiple input "
"images");
ret = -1;
goto out;
}
qemu_progress_init(progress, 2.0);
qemu_progress_print(0, 100);
bs = g_malloc0(bs_n * sizeof(BlockDriverState *));
total_sectors = 0;
for (bs_i = 0; bs_i < bs_n; bs_i++) {
bs[bs_i] = bdrv_new_open(argv[optind + bs_i], fmt, BDRV_O_FLAGS);
if (!bs[bs_i]) {
error_report("Could not open '%s'", argv[optind + bs_i]);
ret = -1;
goto out;
}
bdrv_get_geometry(bs[bs_i], &bs_sectors);
total_sectors += bs_sectors;
}
if (snapshot_name != NULL) {
if (bs_n > 1) {
error_report("No support for concatenating multiple snapshot");
ret = -1;
goto out;
}
if (bdrv_snapshot_load_tmp(bs[0], snapshot_name) < 0) {
error_report("Failed to load snapshot");
ret = -1;
goto out;
}
}
/* Find driver and parse its options */
drv = bdrv_find_format(out_fmt);
if (!drv) {
error_report("Unknown file format '%s'", out_fmt);
ret = -1;
goto out;
}
proto_drv = bdrv_find_protocol(out_filename);
if (!proto_drv) {
error_report("Unknown protocol '%s'", out_filename);
ret = -1;
goto out;
}
create_options = append_option_parameters(create_options,
drv->create_options);
create_options = append_option_parameters(create_options,
proto_drv->create_options);
if (options) {
param = parse_option_parameters(options, create_options, param);
if (param == NULL) {
error_report("Invalid options for file format '%s'.", out_fmt);
ret = -1;
goto out;
}
} else {
param = parse_option_parameters("", create_options, param);
}
set_option_parameter_int(param, BLOCK_OPT_SIZE, total_sectors * 512);
ret = add_old_style_options(out_fmt, param, out_baseimg, NULL);
if (ret < 0) {
goto out;
}
/* Get backing file name if -o backing_file was used */
out_baseimg_param = get_option_parameter(param, BLOCK_OPT_BACKING_FILE);
if (out_baseimg_param) {
out_baseimg = out_baseimg_param->value.s;
}
/* Check if compression is supported */
if (compress) {
QEMUOptionParameter *encryption =
get_option_parameter(param, BLOCK_OPT_ENCRYPT);
QEMUOptionParameter *preallocation =
get_option_parameter(param, BLOCK_OPT_PREALLOC);
if (!drv->bdrv_write_compressed) {
error_report("Compression not supported for this file format");
ret = -1;
goto out;
}
if (encryption && encryption->value.n) {
error_report("Compression and encryption not supported at "
"the same time");
ret = -1;
goto out;
}
if (preallocation && preallocation->value.s
&& strcmp(preallocation->value.s, "off"))
{
error_report("Compression and preallocation not supported at "
"the same time");
ret = -1;
goto out;
}
}
/* Create the new image */
ret = bdrv_create(drv, out_filename, param);
if (ret < 0) {
if (ret == -ENOTSUP) {
error_report("Formatting not supported for file format '%s'",
out_fmt);
} else if (ret == -EFBIG) {
error_report("The image size is too large for file format '%s'",
out_fmt);
} else {
error_report("%s: error while converting %s: %s",
out_filename, out_fmt, strerror(-ret));
}
goto out;
}
flags = BDRV_O_RDWR;
ret = bdrv_parse_cache_flags(cache, &flags);
if (ret < 0) {
error_report("Invalid cache option: %s", cache);
return -1;
}
out_bs = bdrv_new_open(out_filename, out_fmt, flags);
if (!out_bs) {
ret = -1;
goto out;
}
bs_i = 0;
bs_offset = 0;
bdrv_get_geometry(bs[0], &bs_sectors);
buf = qemu_blockalign(out_bs, IO_BUF_SIZE);
if (compress) {
ret = bdrv_get_info(out_bs, &bdi);
if (ret < 0) {
error_report("could not get block driver info");
goto out;
}
cluster_size = bdi.cluster_size;
if (cluster_size <= 0 || cluster_size > IO_BUF_SIZE) {
error_report("invalid cluster size");
ret = -1;
goto out;
}
cluster_sectors = cluster_size >> 9;
sector_num = 0;
nb_sectors = total_sectors;
local_progress = (float)100 /
(nb_sectors / MIN(nb_sectors, cluster_sectors));
for(;;) {
int64_t bs_num;
int remainder;
uint8_t *buf2;
nb_sectors = total_sectors - sector_num;
if (nb_sectors <= 0)
break;
if (nb_sectors >= cluster_sectors)
n = cluster_sectors;
else
n = nb_sectors;
bs_num = sector_num - bs_offset;
assert (bs_num >= 0);
remainder = n;
buf2 = buf;
while (remainder > 0) {
int nlow;
while (bs_num == bs_sectors) {
bs_i++;
assert (bs_i < bs_n);
bs_offset += bs_sectors;
bdrv_get_geometry(bs[bs_i], &bs_sectors);
bs_num = 0;
/* printf("changing part: sector_num=%" PRId64 ", "
"bs_i=%d, bs_offset=%" PRId64 ", bs_sectors=%" PRId64
"\n", sector_num, bs_i, bs_offset, bs_sectors); */
}
assert (bs_num < bs_sectors);
nlow = (remainder > bs_sectors - bs_num) ? bs_sectors - bs_num : remainder;
ret = bdrv_read(bs[bs_i], bs_num, buf2, nlow);
if (ret < 0) {
error_report("error while reading sector %" PRId64 ": %s",
bs_num, strerror(-ret));
goto out;
}
buf2 += nlow * 512;
bs_num += nlow;
remainder -= nlow;
}
assert (remainder == 0);
if (n < cluster_sectors) {
memset(buf + n * 512, 0, cluster_size - n * 512);
}
if (!buffer_is_zero(buf, cluster_size)) {
ret = bdrv_write_compressed(out_bs, sector_num, buf,
cluster_sectors);
if (ret != 0) {
error_report("error while compressing sector %" PRId64
": %s", sector_num, strerror(-ret));
goto out;
}
}
sector_num += n;
qemu_progress_print(local_progress, 100);
}
/* signal EOF to align */
bdrv_write_compressed(out_bs, 0, NULL, 0);
} else {
