static void write_boot_rom(DriveInfo *dinfo, hwaddr addr, size_t rom_size,
Error **errp)
{
BlockBackend *blk = blk_by_legacy_dinfo(dinfo);
uint8_t *storage;
int64_t size;
/* The block backend size should have already been 'validated' by
* the creation of the m25p80 object.
*/
size = blk_getlength(blk);
if (size <= 0) {
error_setg(errp, "failed to get flash size");
return;
}
if (rom_size > size) {
rom_size = size;
}
storage = g_new0(uint8_t, rom_size);
if (blk_pread(blk, 0, storage, rom_size) < 0) {
error_setg(errp, "failed to read the initial flash content");
return;
}
rom_add_blob_fixed("aspeed.boot_rom", storage, rom_size, addr);
g_free(storage);
}
/*
* translate request into iovec + start offset
* do sanity checks along the way
*/
static int xen_block_parse_request(XenBlockRequest *request)
{
XenBlockDataPlane *dataplane = request->dataplane;
size_t len;
int i;
switch (request->req.operation) {
case BLKIF_OP_READ:
break;
case BLKIF_OP_FLUSH_DISKCACHE:
request->presync = 1;
if (!request->req.nr_segments) {
return 0;
}
/* fall through */
case BLKIF_OP_WRITE:
break;
case BLKIF_OP_DISCARD:
return 0;
default:
error_report("error: unknown operation (%d)", request->req.operation);
goto err;
};
if (request->req.operation != BLKIF_OP_READ &&
blk_is_read_only(dataplane->blk)) {
error_report("error: write req for ro device");
goto err;
}
request->start = request->req.sector_number * XEN_BLKIF_SECTOR_SIZE;
for (i = 0; i < request->req.nr_segments; i++) {
if (i == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
error_report("error: nr_segments too big");
goto err;
}
if (request->req.seg[i].first_sect > request->req.seg[i].last_sect) {
error_report("error: first > last sector");
goto err;
}
if (request->req.seg[i].last_sect * XEN_BLKIF_SECTOR_SIZE >=
XC_PAGE_SIZE) {
error_report("error: page crossing");
goto err;
}
len = (request->req.seg[i].last_sect -
request->req.seg[i].first_sect + 1) * XEN_BLKIF_SECTOR_SIZE;
request->size += len;
}
if (request->start + request->size > blk_getlength(dataplane->blk)) {
error_report("error: access beyond end of file");
goto err;
}
return 0;
err:
request->status = BLKIF_RSP_ERROR;
return -1;
}
static void nand_realize(DeviceState *dev, Error **errp)
{
int pagesize;
NANDFlashState *s = NAND(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_setg(errp, "Unsupported NAND block size %#x\n",
1 << s->page_shift);
return;
}
pagesize = 1 << s->oob_shift;
s->mem_oob = 1;
if (s->blk) {
if (blk_is_read_only(s->blk)) {
error_setg(errp, "Can't use a read-only drive");
return;
}
if (blk_getlength(s->blk) >=
(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;
}
static int spapr_nvram_init(VIOsPAPRDevice *dev)
{
sPAPRNVRAM *nvram = VIO_SPAPR_NVRAM(dev);
if (nvram->blk) {
nvram->size = blk_getlength(nvram->blk);
} 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;
}
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);
}
int main(int argc, char **argv)
{
BlockBackend *blk;
BlockDriverState *bs;
off_t dev_offset = 0;
uint16_t nbdflags = 0;
bool disconnect = false;
const char *bindto = NULL;
const char *port = NULL;
char *sockpath = NULL;
char *device = NULL;
off_t fd_size;
QemuOpts *sn_opts = NULL;
const char *sn_id_or_name = NULL;
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:x:T:D:";
struct option lopt[] = {
{ "help", no_argument, NULL, 'h' },
{ "version", no_argument, NULL, 'V' },
{ "bind", required_argument, NULL, 'b' },
{ "port", required_argument, NULL, 'p' },
{ "socket", required_argument, NULL, 'k' },
{ "offset", required_argument, NULL, 'o' },
{ "read-only", no_argument, NULL, 'r' },
{ "partition", required_argument, NULL, 'P' },
{ "connect", required_argument, NULL, 'c' },
{ "disconnect", no_argument, NULL, 'd' },
{ "snapshot", no_argument, NULL, 's' },
{ "load-snapshot", required_argument, NULL, 'l' },
{ "nocache", no_argument, NULL, 'n' },
{ "cache", required_argument, NULL, QEMU_NBD_OPT_CACHE },
{ "aio", required_argument, NULL, QEMU_NBD_OPT_AIO },
{ "discard", required_argument, NULL, QEMU_NBD_OPT_DISCARD },
{ "detect-zeroes", required_argument, NULL,
QEMU_NBD_OPT_DETECT_ZEROES },
{ "shared", required_argument, NULL, 'e' },
{ "format", required_argument, NULL, 'f' },
{ "persistent", no_argument, NULL, 't' },
{ "verbose", no_argument, NULL, 'v' },
{ "object", required_argument, NULL, QEMU_NBD_OPT_OBJECT },
{ "export-name", required_argument, NULL, 'x' },
{ "description", required_argument, NULL, 'D' },
{ "tls-creds", required_argument, NULL, QEMU_NBD_OPT_TLSCREDS },
{ "image-opts", no_argument, NULL, QEMU_NBD_OPT_IMAGE_OPTS },
{ "trace", required_argument, NULL, 'T' },
{ "fork", no_argument, NULL, QEMU_NBD_OPT_FORK },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret = 0;
bool seen_cache = false;
bool seen_discard = false;
bool seen_aio = false;
pthread_t client_thread;
const char *fmt = NULL;
Error *local_err = NULL;
BlockdevDetectZeroesOptions detect_zeroes = BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
QDict *options = NULL;
const char *export_name = NULL;
const char *export_description = NULL;
const char *tlscredsid = NULL;
bool imageOpts = false;
bool writethrough = true;
char *trace_file = NULL;
bool fork_process = false;
int old_stderr = -1;
unsigned socket_activation;
/* The client thread uses SIGTERM to interrupt the server. A signal
* handler ensures that "qemu-nbd -v -c" exits with a nice status code.
*/
struct sigaction sa_sigterm;
memset(&sa_sigterm, 0, sizeof(sa_sigterm));
sa_sigterm.sa_handler = termsig_handler;
sigaction(SIGTERM, &sa_sigterm, NULL);
#ifdef CONFIG_POSIX
signal(SIGPIPE, SIG_IGN);
#endif
module_call_init(MODULE_INIT_TRACE);
qcrypto_init(&error_fatal);
module_call_init(MODULE_INIT_QOM);
qemu_add_opts(&qemu_object_opts);
qemu_add_opts(&qemu_trace_opts);
qemu_init_exec_dir(argv[0]);
while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) {
switch (ch) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
optarg = (char *) "none";
/* fallthrough */
case QEMU_NBD_OPT_CACHE:
if (seen_cache) {
error_report("-n and --cache can only be specified once");
exit(EXIT_FAILURE);
}
seen_cache = true;
if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) == -1) {
error_report("Invalid cache mode `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case QEMU_NBD_OPT_AIO:
if (seen_aio) {
error_report("--aio can only be specified once");
exit(EXIT_FAILURE);
}
seen_aio = true;
if (!strcmp(optarg, "native")) {
flags |= BDRV_O_NATIVE_AIO;
} else if (!strcmp(optarg, "threads")) {
/* this is the default */
} else {
error_report("invalid aio mode `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case QEMU_NBD_OPT_DISCARD:
if (seen_discard) {
error_report("--discard can only be specified once");
exit(EXIT_FAILURE);
}
seen_discard = true;
if (bdrv_parse_discard_flags(optarg, &flags) == -1) {
error_report("Invalid discard mode `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case QEMU_NBD_OPT_DETECT_ZEROES:
detect_zeroes =
qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
optarg,
BLOCKDEV_DETECT_ZEROES_OPTIONS__MAX,
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_err);
if (local_err) {
error_reportf_err(local_err,
"Failed to parse detect_zeroes mode: ");
exit(EXIT_FAILURE);
}
if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
!(flags & BDRV_O_UNMAP)) {
error_report("setting detect-zeroes to unmap is not allowed "
"without setting discard operation to unmap");
exit(EXIT_FAILURE);
}
break;
case 'b':
bindto = optarg;
break;
case 'p':
port = optarg;
break;
case 'o':
dev_offset = strtoll (optarg, &end, 0);
if (*end) {
error_report("Invalid offset `%s'", optarg);
exit(EXIT_FAILURE);
}
if (dev_offset < 0) {
error_report("Offset must be positive `%s'", optarg);
exit(EXIT_FAILURE);
}
break;
case 'l':
if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
optarg, false);
if (!sn_opts) {
error_report("Failed in parsing snapshot param `%s'",
optarg);
exit(EXIT_FAILURE);
}
} else {
sn_id_or_name = optarg;
}
/* fall through */
case 'r':
nbdflags |= NBD_FLAG_READ_ONLY;
flags &= ~BDRV_O_RDWR;
break;
case 'P':
partition = strtol(optarg, &end, 0);
if (*end) {
error_report("Invalid partition `%s'", optarg);
exit(EXIT_FAILURE);
}
if (partition < 1 || partition > 8) {
error_report("Invalid partition %d", partition);
exit(EXIT_FAILURE);
}
break;
case 'k':
sockpath = optarg;
if (sockpath[0] != '/') {
error_report("socket path must be absolute");
exit(EXIT_FAILURE);
}
break;
case 'd':
disconnect = true;
break;
case 'c':
device = optarg;
break;
case 'e':
shared = strtol(optarg, &end, 0);
if (*end) {
error_report("Invalid shared device number '%s'", optarg);
exit(EXIT_FAILURE);
}
if (shared < 1) {
error_report("Shared device number must be greater than 0");
exit(EXIT_FAILURE);
}
break;
case 'f':
fmt = optarg;
break;
case 't':
persistent = 1;
break;
case 'x':
export_name = optarg;
break;
case 'D':
export_description = optarg;
break;
case 'v':
verbose = 1;
break;
case 'V':
version(argv[0]);
exit(0);
break;
case 'h':
usage(argv[0]);
exit(0);
break;
case '?':
error_report("Try `%s --help' for more information.", argv[0]);
exit(EXIT_FAILURE);
case QEMU_NBD_OPT_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
exit(EXIT_FAILURE);
}
} break;
case QEMU_NBD_OPT_TLSCREDS:
tlscredsid = optarg;
break;
case QEMU_NBD_OPT_IMAGE_OPTS:
imageOpts = true;
break;
case 'T':
g_free(trace_file);
trace_file = trace_opt_parse(optarg);
break;
case QEMU_NBD_OPT_FORK:
fork_process = true;
break;
}
}
if ((argc - optind) != 1) {
error_report("Invalid number of arguments");
error_printf("Try `%s --help' for more information.\n", argv[0]);
exit(EXIT_FAILURE);
}
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
exit(EXIT_FAILURE);
}
if (!trace_init_backends()) {
exit(1);
}
trace_init_file(trace_file);
qemu_set_log(LOG_TRACE);
socket_activation = check_socket_activation();
if (socket_activation == 0) {
setup_address_and_port(&bindto, &port);
} else {
/* Using socket activation - check user didn't use -p etc. */
const char *err_msg = socket_activation_validate_opts(device, sockpath,
bindto, port);
if (err_msg != NULL) {
error_report("%s", err_msg);
exit(EXIT_FAILURE);
}
/* qemu-nbd can only listen on a single socket. */
if (socket_activation > 1) {
error_report("qemu-nbd does not support socket activation with %s > 1",
"LISTEN_FDS");
exit(EXIT_FAILURE);
}
}
if (tlscredsid) {
if (sockpath) {
error_report("TLS is only supported with IPv4/IPv6");
exit(EXIT_FAILURE);
}
if (device) {
error_report("TLS is not supported with a host device");
exit(EXIT_FAILURE);
}
if (!export_name) {
/* Set the default NBD protocol export name, since
* we *must* use new style protocol for TLS */
export_name = "";
}
tlscreds = nbd_get_tls_creds(tlscredsid, &local_err);
if (local_err) {
error_report("Failed to get TLS creds %s",
error_get_pretty(local_err));
exit(EXIT_FAILURE);
}
}
if (disconnect) {
int nbdfd = open(argv[optind], O_RDWR);
if (nbdfd < 0) {
error_report("Cannot open %s: %s", argv[optind],
strerror(errno));
exit(EXIT_FAILURE);
}
nbd_disconnect(nbdfd);
close(nbdfd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
if ((device && !verbose) || fork_process) {
int stderr_fd[2];
pid_t pid;
int ret;
if (qemu_pipe(stderr_fd) < 0) {
error_report("Error setting up communication pipe: %s",
strerror(errno));
exit(EXIT_FAILURE);
}
/* Now daemonize, but keep a communication channel open to
* print errors and exit with the proper status code.
*/
pid = fork();
if (pid < 0) {
error_report("Failed to fork: %s", strerror(errno));
exit(EXIT_FAILURE);
} else if (pid == 0) {
close(stderr_fd[0]);
ret = qemu_daemon(1, 0);
/* Temporarily redirect stderr to the parent's pipe... */
old_stderr = dup(STDERR_FILENO);
dup2(stderr_fd[1], STDERR_FILENO);
if (ret < 0) {
error_report("Failed to daemonize: %s", strerror(errno));
exit(EXIT_FAILURE);
}
/* ... close the descriptor we inherited and go on. */
close(stderr_fd[1]);
} else {
bool errors = false;
char *buf;
/* In the parent. Print error messages from the child until
* it closes the pipe.
*/
close(stderr_fd[1]);
buf = g_malloc(1024);
while ((ret = read(stderr_fd[0], buf, 1024)) > 0) {
errors = true;
ret = qemu_write_full(STDERR_FILENO, buf, ret);
if (ret < 0) {
exit(EXIT_FAILURE);
}
}
if (ret < 0) {
error_report("Cannot read from daemon: %s",
strerror(errno));
exit(EXIT_FAILURE);
}
/* Usually the daemon should not print any message.
* Exit with zero status in that case.
*/
exit(errors);
}
}
if (device != NULL && sockpath == NULL) {
sockpath = g_malloc(128);
snprintf(sockpath, 128, SOCKET_PATH, basename(device));
}
if (socket_activation == 0) {
server_ioc = qio_channel_socket_new();
saddr = nbd_build_socket_address(sockpath, bindto, port);
if (qio_channel_socket_listen_sync(server_ioc, saddr, &local_err) < 0) {
object_unref(OBJECT(server_ioc));
error_report_err(local_err);
return 1;
}
} else {
/* See comment in check_socket_activation above. */
assert(socket_activation == 1);
server_ioc = qio_channel_socket_new_fd(FIRST_SOCKET_ACTIVATION_FD,
&local_err);
if (server_ioc == NULL) {
error_report("Failed to use socket activation: %s",
error_get_pretty(local_err));
exit(EXIT_FAILURE);
}
}
if (qemu_init_main_loop(&local_err)) {
error_report_err(local_err);
exit(EXIT_FAILURE);
}
bdrv_init();
atexit(bdrv_close_all);
srcpath = argv[optind];
if (imageOpts) {
QemuOpts *opts;
if (fmt) {
error_report("--image-opts and -f are mutually exclusive");
exit(EXIT_FAILURE);
}
opts = qemu_opts_parse_noisily(&file_opts, srcpath, true);
if (!opts) {
qemu_opts_reset(&file_opts);
exit(EXIT_FAILURE);
}
options = qemu_opts_to_qdict(opts, NULL);
qemu_opts_reset(&file_opts);
blk = blk_new_open(NULL, NULL, options, flags, &local_err);
} else {
if (fmt) {
options = qdict_new();
qdict_put_str(options, "driver", fmt);
}
blk = blk_new_open(srcpath, NULL, options, flags, &local_err);
}
if (!blk) {
error_reportf_err(local_err, "Failed to blk_new_open '%s': ",
argv[optind]);
exit(EXIT_FAILURE);
}
bs = blk_bs(blk);
blk_set_enable_write_cache(blk, !writethrough);
if (sn_opts) {
ret = bdrv_snapshot_load_tmp(bs,
qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
&local_err);
} else if (sn_id_or_name) {
ret = bdrv_snapshot_load_tmp_by_id_or_name(bs, sn_id_or_name,
&local_err);
}
if (ret < 0) {
error_reportf_err(local_err, "Failed to load snapshot: ");
exit(EXIT_FAILURE);
}
bs->detect_zeroes = detect_zeroes;
fd_size = blk_getlength(blk);
if (fd_size < 0) {
error_report("Failed to determine the image length: %s",
strerror(-fd_size));
exit(EXIT_FAILURE);
}
if (dev_offset >= fd_size) {
error_report("Offset (%lld) has to be smaller than the image size "
"(%lld)",
(long long int)dev_offset, (long long int)fd_size);
exit(EXIT_FAILURE);
}
fd_size -= dev_offset;
if (partition != -1) {
ret = find_partition(blk, partition, &dev_offset, &fd_size);
if (ret < 0) {
error_report("Could not find partition %d: %s", partition,
strerror(-ret));
exit(EXIT_FAILURE);
}
}
exp = nbd_export_new(bs, dev_offset, fd_size, nbdflags, nbd_export_closed,
writethrough, NULL, &local_err);
if (!exp) {
error_report_err(local_err);
exit(EXIT_FAILURE);
}
if (export_name) {
nbd_export_set_name(exp, export_name);
nbd_export_set_description(exp, export_description);
newproto = true;
} else if (export_description) {
error_report("Export description requires an export name");
exit(EXIT_FAILURE);
}
if (device) {
int ret;
ret = pthread_create(&client_thread, NULL, nbd_client_thread, device);
if (ret != 0) {
error_report("Failed to create client thread: %s", strerror(ret));
exit(EXIT_FAILURE);
}
} else {
/* Shut up GCC warnings. */
memset(&client_thread, 0, sizeof(client_thread));
}
nbd_update_server_watch();
/* now when the initialization is (almost) complete, chdir("/")
* to free any busy filesystems */
if (chdir("/") < 0) {
error_report("Could not chdir to root directory: %s",
strerror(errno));
exit(EXIT_FAILURE);
}
if (fork_process) {
dup2(old_stderr, STDERR_FILENO);
close(old_stderr);
}
state = RUNNING;
do {
main_loop_wait(false);
if (state == TERMINATE) {
state = TERMINATING;
nbd_export_close(exp);
nbd_export_put(exp);
exp = NULL;
}
} while (state != TERMINATED);
blk_unref(blk);
if (sockpath) {
unlink(sockpath);
}
qemu_opts_del(sn_opts);
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
/* commit COW file into the raw image */
int bdrv_commit(BlockDriverState *bs)
{
BlockBackend *src, *backing;
BlockDriverState *backing_file_bs = NULL;
BlockDriverState *commit_top_bs = NULL;
BlockDriver *drv = bs->drv;
int64_t offset, length, backing_length;
int ro;
int64_t n;
int ret = 0;
uint8_t *buf = NULL;
Error *local_err = NULL;
if (!drv)
return -ENOMEDIUM;
if (!bs->backing) {
return -ENOTSUP;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) ||
bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) {
return -EBUSY;
}
ro = bs->backing->bs->read_only;
if (ro) {
if (bdrv_reopen_set_read_only(bs->backing->bs, false, NULL)) {
return -EACCES;
}
}
src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
ret = blk_insert_bs(src, bs, &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
}
/* Insert commit_top block node above backing, so we can write to it */
backing_file_bs = backing_bs(bs);
commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
&local_err);
if (commit_top_bs == NULL) {
error_report_err(local_err);
goto ro_cleanup;
}
bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(backing_file_bs));
bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
ret = blk_insert_bs(backing, backing_file_bs, &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
}
length = blk_getlength(src);
if (length < 0) {
ret = length;
goto ro_cleanup;
}
backing_length = blk_getlength(backing);
if (backing_length < 0) {
ret = backing_length;
goto ro_cleanup;
}
/* If our top snapshot is larger than the backing file image,
* grow the backing file image if possible. If not possible,
* we must return an error */
if (length > backing_length) {
ret = blk_truncate(backing, length, PREALLOC_MODE_OFF, &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
}
}
/* blk_try_blockalign() for src will choose an alignment that works for
* backing as well, so no need to compare the alignment manually. */
buf = blk_try_blockalign(src, COMMIT_BUF_SIZE);
if (buf == NULL) {
ret = -ENOMEM;
goto ro_cleanup;
}
for (offset = 0; offset < length; offset += n) {
ret = bdrv_is_allocated(bs, offset, COMMIT_BUF_SIZE, &n);
if (ret < 0) {
goto ro_cleanup;
}
if (ret) {
ret = blk_pread(src, offset, buf, n);
if (ret < 0) {
goto ro_cleanup;
}
ret = blk_pwrite(backing, offset, buf, n, 0);
if (ret < 0) {
goto ro_cleanup;
}
}
}
if (drv->bdrv_make_empty) {
ret = drv->bdrv_make_empty(bs);
if (ret < 0) {
goto ro_cleanup;
}
blk_flush(src);
}
/*
* Make sure all data we wrote to the backing device is actually
* stable on disk.
*/
blk_flush(backing);
ret = 0;
ro_cleanup:
qemu_vfree(buf);
blk_unref(backing);
if (backing_file_bs) {
bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
}
bdrv_unref(commit_top_bs);
blk_unref(src);
if (ro) {
/* ignoring error return here */
bdrv_reopen_set_read_only(bs->backing->bs, true, NULL);
}
return ret;
}
static int coroutine_fn commit_run(Job *job, Error **errp)
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
int64_t offset;
uint64_t delay_ns = 0;
int ret = 0;
int64_t n = 0; /* bytes */
void *buf = NULL;
int bytes_written = 0;
int64_t len, base_len;
ret = len = blk_getlength(s->top);
if (len < 0) {
goto out;
}
job_progress_set_remaining(&s->common.job, len);
ret = base_len = blk_getlength(s->base);
if (base_len < 0) {
goto out;
}
if (base_len < len) {
ret = blk_truncate(s->base, len, PREALLOC_MODE_OFF, NULL);
if (ret) {
goto out;
}
}
buf = blk_blockalign(s->top, COMMIT_BUFFER_SIZE);
for (offset = 0; offset < len; offset += n) {
bool copy;
/* Note that even when no rate limit is applied we need to yield
* with no pending I/O here so that bdrv_drain_all() returns.
*/
job_sleep_ns(&s->common.job, delay_ns);
if (job_is_cancelled(&s->common.job)) {
break;
}
/* Copy if allocated above the base */
ret = bdrv_is_allocated_above(blk_bs(s->top), blk_bs(s->base),
offset, COMMIT_BUFFER_SIZE, &n);
copy = (ret == 1);
trace_commit_one_iteration(s, offset, n, ret);
if (copy) {
ret = commit_populate(s->top, s->base, offset, n, buf);
bytes_written += n;
}
if (ret < 0) {
BlockErrorAction action =
block_job_error_action(&s->common, false, s->on_error, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT) {
goto out;
} else {
n = 0;
continue;
}
}
/* Publish progress */
job_progress_update(&s->common.job, n);
if (copy) {
delay_ns = block_job_ratelimit_get_delay(&s->common, n);
} else {
delay_ns = 0;
}
}
ret = 0;
out:
qemu_vfree(buf);
return ret;
}
int main(int argc, char **argv)
{
BlockBackend *blk;
BlockDriverState *bs;
off_t dev_offset = 0;
uint32_t nbdflags = 0;
bool disconnect = false;
const char *bindto = "0.0.0.0";
const char *port = NULL;
char *sockpath = NULL;
char *device = NULL;
off_t fd_size;
QemuOpts *sn_opts = NULL;
const char *sn_id_or_name = NULL;
const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:";
struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "bind", 1, NULL, 'b' },
{ "port", 1, NULL, 'p' },
{ "socket", 1, NULL, 'k' },
{ "offset", 1, NULL, 'o' },
{ "read-only", 0, NULL, 'r' },
{ "partition", 1, NULL, 'P' },
{ "connect", 1, NULL, 'c' },
{ "disconnect", 0, NULL, 'd' },
{ "snapshot", 0, NULL, 's' },
{ "load-snapshot", 1, NULL, 'l' },
{ "nocache", 0, NULL, 'n' },
{ "cache", 1, NULL, QEMU_NBD_OPT_CACHE },
{ "aio", 1, NULL, QEMU_NBD_OPT_AIO },
{ "discard", 1, NULL, QEMU_NBD_OPT_DISCARD },
{ "detect-zeroes", 1, NULL, QEMU_NBD_OPT_DETECT_ZEROES },
{ "shared", 1, NULL, 'e' },
{ "format", 1, NULL, 'f' },
{ "persistent", 0, NULL, 't' },
{ "verbose", 0, NULL, 'v' },
{ NULL, 0, NULL, 0 }
};
int ch;
int opt_ind = 0;
char *end;
int flags = BDRV_O_RDWR;
int partition = -1;
int ret = 0;
int fd;
bool seen_cache = false;
bool seen_discard = false;
bool seen_aio = false;
pthread_t client_thread;
const char *fmt = NULL;
Error *local_err = NULL;
BlockdevDetectZeroesOptions detect_zeroes = BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
QDict *options = NULL;
/* The client thread uses SIGTERM to interrupt the server. A signal
* handler ensures that "qemu-nbd -v -c" exits with a nice status code.
*/
struct sigaction sa_sigterm;
memset(&sa_sigterm, 0, sizeof(sa_sigterm));
sa_sigterm.sa_handler = termsig_handler;
sigaction(SIGTERM, &sa_sigterm, NULL);
qemu_init_exec_dir(argv[0]);
while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) {
switch (ch) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
optarg = (char *) "none";
/* fallthrough */
case QEMU_NBD_OPT_CACHE:
if (seen_cache) {
errx(EXIT_FAILURE, "-n and --cache can only be specified once");
}
seen_cache = true;
if (bdrv_parse_cache_flags(optarg, &flags) == -1) {
errx(EXIT_FAILURE, "Invalid cache mode `%s'", optarg);
}
break;
case QEMU_NBD_OPT_AIO:
if (seen_aio) {
errx(EXIT_FAILURE, "--aio can only be specified once");
}
seen_aio = true;
if (!strcmp(optarg, "native")) {
flags |= BDRV_O_NATIVE_AIO;
} else if (!strcmp(optarg, "threads")) {
/* this is the default */
} else {
errx(EXIT_FAILURE, "invalid aio mode `%s'", optarg);
}
break;
case QEMU_NBD_OPT_DISCARD:
if (seen_discard) {
errx(EXIT_FAILURE, "--discard can only be specified once");
}
seen_discard = true;
if (bdrv_parse_discard_flags(optarg, &flags) == -1) {
errx(EXIT_FAILURE, "Invalid discard mode `%s'", optarg);
}
break;
case QEMU_NBD_OPT_DETECT_ZEROES:
detect_zeroes =
qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
optarg,
BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_err);
if (local_err) {
errx(EXIT_FAILURE, "Failed to parse detect_zeroes mode: %s",
error_get_pretty(local_err));
}
if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
!(flags & BDRV_O_UNMAP)) {
errx(EXIT_FAILURE, "setting detect-zeroes to unmap is not allowed "
"without setting discard operation to unmap");
}
break;
case 'b':
bindto = optarg;
break;
case 'p':
port = optarg;
break;
case 'o':
dev_offset = strtoll (optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid offset `%s'", optarg);
}
if (dev_offset < 0) {
errx(EXIT_FAILURE, "Offset must be positive `%s'", optarg);
}
break;
case 'l':
if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
optarg, false);
if (!sn_opts) {
errx(EXIT_FAILURE, "Failed in parsing snapshot param `%s'",
optarg);
}
} else {
sn_id_or_name = optarg;
}
/* fall through */
case 'r':
nbdflags |= NBD_FLAG_READ_ONLY;
flags &= ~BDRV_O_RDWR;
break;
case 'P':
partition = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid partition `%s'", optarg);
}
if (partition < 1 || partition > 8) {
errx(EXIT_FAILURE, "Invalid partition %d", partition);
}
break;
case 'k':
sockpath = optarg;
if (sockpath[0] != '/') {
errx(EXIT_FAILURE, "socket path must be absolute\n");
}
break;
case 'd':
disconnect = true;
break;
case 'c':
device = optarg;
break;
case 'e':
shared = strtol(optarg, &end, 0);
if (*end) {
errx(EXIT_FAILURE, "Invalid shared device number '%s'", optarg);
}
if (shared < 1) {
errx(EXIT_FAILURE, "Shared device number must be greater than 0\n");
}
break;
case 'f':
fmt = optarg;
break;
case 't':
persistent = 1;
break;
case 'v':
verbose = 1;
break;
case 'V':
version(argv[0]);
exit(0);
break;
case 'h':
usage(argv[0]);
exit(0);
break;
case '?':
errx(EXIT_FAILURE, "Try `%s --help' for more information.",
argv[0]);
}
}
if ((argc - optind) != 1) {
errx(EXIT_FAILURE, "Invalid number of argument.\n"
"Try `%s --help' for more information.",
argv[0]);
}
if (disconnect) {
fd = open(argv[optind], O_RDWR);
if (fd < 0) {
err(EXIT_FAILURE, "Cannot open %s", argv[optind]);
}
nbd_disconnect(fd);
close(fd);
printf("%s disconnected\n", argv[optind]);
return 0;
}
if (device && !verbose) {
int stderr_fd[2];
pid_t pid;
int ret;
if (qemu_pipe(stderr_fd) < 0) {
err(EXIT_FAILURE, "Error setting up communication pipe");
}
/* Now daemonize, but keep a communication channel open to
* print errors and exit with the proper status code.
*/
pid = fork();
if (pid < 0) {
err(EXIT_FAILURE, "Failed to fork");
} else if (pid == 0) {
close(stderr_fd[0]);
ret = qemu_daemon(1, 0);
/* Temporarily redirect stderr to the parent's pipe... */
dup2(stderr_fd[1], STDERR_FILENO);
if (ret < 0) {
err(EXIT_FAILURE, "Failed to daemonize");
}
/* ... close the descriptor we inherited and go on. */
close(stderr_fd[1]);
} else {
bool errors = false;
char *buf;
/* In the parent. Print error messages from the child until
* it closes the pipe.
*/
close(stderr_fd[1]);
buf = g_malloc(1024);
while ((ret = read(stderr_fd[0], buf, 1024)) > 0) {
errors = true;
ret = qemu_write_full(STDERR_FILENO, buf, ret);
if (ret < 0) {
exit(EXIT_FAILURE);
}
}
if (ret < 0) {
err(EXIT_FAILURE, "Cannot read from daemon");
}
/* Usually the daemon should not print any message.
* Exit with zero status in that case.
*/
exit(errors);
}
}
if (device != NULL && sockpath == NULL) {
sockpath = g_malloc(128);
snprintf(sockpath, 128, SOCKET_PATH, basename(device));
}
saddr = nbd_build_socket_address(sockpath, bindto, port);
if (qemu_init_main_loop(&local_err)) {
error_report_err(local_err);
exit(EXIT_FAILURE);
}
bdrv_init();
atexit(bdrv_close_all);
if (fmt) {
options = qdict_new();
qdict_put(options, "driver", qstring_from_str(fmt));
}
srcpath = argv[optind];
blk = blk_new_open("hda", srcpath, NULL, options, flags, &local_err);
if (!blk) {
errx(EXIT_FAILURE, "Failed to blk_new_open '%s': %s", argv[optind],
error_get_pretty(local_err));
}
bs = blk_bs(blk);
if (sn_opts) {
ret = bdrv_snapshot_load_tmp(bs,
qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
&local_err);
} else if (sn_id_or_name) {
ret = bdrv_snapshot_load_tmp_by_id_or_name(bs, sn_id_or_name,
&local_err);
}
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE,
"Failed to load snapshot: %s",
error_get_pretty(local_err));
}
bs->detect_zeroes = detect_zeroes;
fd_size = blk_getlength(blk);
if (fd_size < 0) {
errx(EXIT_FAILURE, "Failed to determine the image length: %s",
strerror(-fd_size));
}
if (partition != -1) {
ret = find_partition(blk, partition, &dev_offset, &fd_size);
if (ret < 0) {
errno = -ret;
err(EXIT_FAILURE, "Could not find partition %d", partition);
}
}
exp = nbd_export_new(blk, dev_offset, fd_size, nbdflags, nbd_export_closed,
&local_err);
if (!exp) {
errx(EXIT_FAILURE, "%s", error_get_pretty(local_err));
}
fd = socket_listen(saddr, &local_err);
if (fd < 0) {
error_report_err(local_err);
return 1;
}
if (device) {
int ret;
ret = pthread_create(&client_thread, NULL, nbd_client_thread, device);
if (ret != 0) {
errx(EXIT_FAILURE, "Failed to create client thread: %s",
strerror(ret));
}
} else {
/* Shut up GCC warnings. */
memset(&client_thread, 0, sizeof(client_thread));
}
server_fd = fd;
nbd_update_server_fd_handler(fd);
/* now when the initialization is (almost) complete, chdir("/")
* to free any busy filesystems */
if (chdir("/") < 0) {
err(EXIT_FAILURE, "Could not chdir to root directory");
}
state = RUNNING;
do {
main_loop_wait(false);
if (state == TERMINATE) {
state = TERMINATING;
nbd_export_close(exp);
nbd_export_put(exp);
exp = NULL;
}
} while (state != TERMINATED);
blk_unref(blk);
if (sockpath) {
unlink(sockpath);
}
qemu_opts_del(sn_opts);
if (device) {
void *ret;
pthread_join(client_thread, &ret);
exit(ret != NULL);
} else {
exit(EXIT_SUCCESS);
}
}
static int blk_connect(struct XenDevice *xendev)
{
struct XenBlkDev *blkdev = container_of(xendev, struct XenBlkDev, xendev);
int index, qflags;
bool readonly = true;
bool writethrough = true;
int order, ring_ref;
unsigned int ring_size, max_grants;
unsigned int i;
trace_xen_disk_connect(xendev->name);
/* read-only ? */
if (blkdev->directiosafe) {
qflags = BDRV_O_NOCACHE | BDRV_O_NATIVE_AIO;
} else {
qflags = 0;
writethrough = false;
}
if (strcmp(blkdev->mode, "w") == 0) {
qflags |= BDRV_O_RDWR;
readonly = false;
}
if (blkdev->feature_discard) {
qflags |= BDRV_O_UNMAP;
}
/* init qemu block driver */
index = (xendev->dev - 202 * 256) / 16;
blkdev->dinfo = drive_get(IF_XEN, 0, index);
if (!blkdev->dinfo) {
Error *local_err = NULL;
QDict *options = NULL;
if (strcmp(blkdev->fileproto, "<unset>")) {
options = qdict_new();
qdict_put_str(options, "driver", blkdev->fileproto);
}
/* setup via xenbus -> create new block driver instance */
xen_pv_printf(xendev, 2, "create new bdrv (xenbus setup)\n");
blkdev->blk = blk_new_open(blkdev->filename, NULL, options,
qflags, &local_err);
if (!blkdev->blk) {
xen_pv_printf(xendev, 0, "error: %s\n",
error_get_pretty(local_err));
error_free(local_err);
return -1;
}
blk_set_enable_write_cache(blkdev->blk, !writethrough);
} else {
/* setup via qemu cmdline -> already setup for us */
xen_pv_printf(xendev, 2,
"get configured bdrv (cmdline setup)\n");
blkdev->blk = blk_by_legacy_dinfo(blkdev->dinfo);
if (blk_is_read_only(blkdev->blk) && !readonly) {
xen_pv_printf(xendev, 0, "Unexpected read-only drive");
blkdev->blk = NULL;
return -1;
}
/* blkdev->blk is not create by us, we get a reference
* so we can blk_unref() unconditionally */
blk_ref(blkdev->blk);
}
blk_attach_dev_legacy(blkdev->blk, blkdev);
blkdev->file_size = blk_getlength(blkdev->blk);
if (blkdev->file_size < 0) {
BlockDriverState *bs = blk_bs(blkdev->blk);
const char *drv_name = bs ? bdrv_get_format_name(bs) : NULL;
xen_pv_printf(xendev, 1, "blk_getlength: %d (%s) | drv %s\n",
(int)blkdev->file_size, strerror(-blkdev->file_size),
drv_name ?: "-");
blkdev->file_size = 0;
}