/* Disable dataplane thread during live migration since it does not
* update the dirty memory bitmap yet.
*/
static void virtio_blk_migration_state_changed(Notifier *notifier, void *data)
{
VirtIOBlock *s = container_of(notifier, VirtIOBlock,
migration_state_notifier);
MigrationState *mig = data;
Error *err = NULL;
if (migration_in_setup(mig)) {
if (!s->dataplane) {
return;
}
virtio_blk_data_plane_destroy(s->dataplane);
s->dataplane = NULL;
} else if (migration_has_finished(mig) ||
migration_has_failed(mig)) {
if (s->dataplane) {
return;
}
bdrv_drain_all(); /* complete in-flight non-dataplane requests */
virtio_blk_data_plane_create(VIRTIO_DEVICE(s), &s->blk,
&s->dataplane, &err);
if (err != NULL) {
error_report("%s", error_get_pretty(err));
error_free(err);
}
}
}
/**
* Delete an internal snapshot by @snapshot_id and @name.
* @bs: block device used in the operation
* @snapshot_id: unique snapshot ID, or NULL
* @name: snapshot name, or NULL
* @errp: location to store error
*
* If both @snapshot_id and @name are specified, delete the first one with
* id @snapshot_id and name @name.
* If only @snapshot_id is specified, delete the first one with id
* @snapshot_id.
* If only @name is specified, delete the first one with name @name.
* if none is specified, return -EINVAL.
*
* Returns: 0 on success, -errno on failure. If @bs is not inserted, return
* -ENOMEDIUM. If @snapshot_id and @name are both NULL, return -EINVAL. If @bs
* does not support internal snapshot deletion, return -ENOTSUP. If @bs does
* not support parameter @snapshot_id or @name, or one of them is not correctly
* specified, return -EINVAL. If @bs can't find one matching @id and @name,
* return -ENOENT. If @errp != NULL, it will always be filled with error
* message on failure.
*/
int bdrv_snapshot_delete(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
BlockDriver *drv = bs->drv;
if (!drv) {
error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
return -ENOMEDIUM;
}
if (!snapshot_id && !name) {
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
/* drain all pending i/o before deleting snapshot */
bdrv_drain_all();
if (drv->bdrv_snapshot_delete) {
return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
}
if (bs->file) {
return bdrv_snapshot_delete(bs->file, snapshot_id, name, errp);
}
error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
drv->format_name, bdrv_get_device_name(bs),
"internal snapshot deletion");
return -ENOTSUP;
}
int simple_bus_fdt_init(char *bus_node_path, FDTMachineInfo *fdti, void *unused)
{
int i;
int num_children = qemu_devtree_get_num_children(fdti->fdt, bus_node_path,
1);
char **children = qemu_devtree_get_children(fdti->fdt, bus_node_path, 1);
int initialRoutinesPending = fdti->routinesPending;
DB_PRINT("num child devices: %d\n", num_children);
for (i = 0; i < num_children; i++) {
struct FDTInitNodeArgs *init_args = g_malloc0(sizeof(*init_args));
init_args->node_path = children[i];
init_args->fdti = fdti;
fdti->routinesPending++;
qemu_coroutine_enter(qemu_coroutine_create(fdt_init_node), init_args);
}
if (fdti->routinesPending != initialRoutinesPending) {
bdrv_drain_all();
}
g_free(children);
return 0;
}
static void virtio_blk_reset(VirtIODevice *vdev)
{
/*
* This should cancel pending requests, but can't do nicely until there
* are per-device request lists.
*/
bdrv_drain_all();
}
static void do_vm_stop(RunState state)
{
if (runstate_is_running()) {
cpu_disable_ticks();
pause_all_vcpus();
runstate_set(state);
vm_state_notify(0, state);
bdrv_drain_all();
bdrv_flush_all();
monitor_protocol_event(QEVENT_STOP, NULL);
}
}
static void virtio_blk_reset(VirtIODevice *vdev)
{
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
VirtIOBlock *s = to_virtio_blk(vdev);
if (s->dataplane) {
virtio_blk_data_plane_stop(s->dataplane);
}
#endif
/*
* This should cancel pending requests, but can't do nicely until there
* are per-device request lists.
*/
bdrv_drain_all();
}
static void virtio_blk_reset(VirtIODevice *vdev)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
if (s->dataplane) {
virtio_blk_data_plane_stop(s->dataplane);
}
#endif
/*
* This should cancel pending requests, but can't do nicely until there
* are per-device request lists.
*/
bdrv_drain_all();
bdrv_set_enable_write_cache(s->bs, s->original_wce);
}
static void platform_fixed_ioport_writew(void *opaque, uint32_t addr, uint32_t val)
{
PCIXenPlatformState *s = opaque;
switch (addr) {
case 0: {
PCIDevice *pci_dev = PCI_DEVICE(s);
/* Unplug devices. Value is a bitmask of which devices to
unplug, with bit 0 the IDE devices, bit 1 the network
devices, and bit 2 the non-primary-master IDE devices. */
if (val & UNPLUG_ALL_IDE_DISKS) {
DPRINTF("unplug disks\n");
bdrv_drain_all();
bdrv_flush_all();
pci_unplug_disks(pci_dev->bus);
}
if (val & UNPLUG_ALL_NICS) {
DPRINTF("unplug nics\n");
pci_unplug_nics(pci_dev->bus);
}
if (val & UNPLUG_AUX_IDE_DISKS) {
DPRINTF("unplug auxiliary disks not supported\n");
}
break;
}
case 2:
switch (val) {
case 1:
DPRINTF("Citrix Windows PV drivers loaded in guest\n");
break;
case 0:
DPRINTF("Guest claimed to be running PV product 0?\n");
break;
default:
DPRINTF("Unknown PV product %d loaded in guest\n", val);
break;
}
s->driver_product_version = val;
break;
}
}
int main(int argc, char **argv)
{
int readonly = 0;
int growable = 0;
const char *sopt = "hVc:d:rsnmgkt:T:";
const struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "offset", 1, NULL, 'o' },
{ "cmd", 1, NULL, 'c' },
{ "read-only", 0, NULL, 'r' },
{ "snapshot", 0, NULL, 's' },
{ "nocache", 0, NULL, 'n' },
{ "misalign", 0, NULL, 'm' },
{ "growable", 0, NULL, 'g' },
{ "native-aio", 0, NULL, 'k' },
{ "discard", 1, NULL, 'd' },
{ "cache", 1, NULL, 't' },
{ "trace", 1, NULL, 'T' },
{ NULL, 0, NULL, 0 }
};
int c;
int opt_index = 0;
int flags = BDRV_O_UNMAP;
progname = basename(argv[0]);
while ((c = getopt_long(argc, argv, sopt, lopt, &opt_index)) != -1) {
switch (c) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
break;
case 'd':
if (bdrv_parse_discard_flags(optarg, &flags) < 0) {
error_report("Invalid discard option: %s", optarg);
exit(1);
}
break;
case 'c':
add_user_command(optarg);
break;
case 'r':
readonly = 1;
break;
case 'm':
misalign = 1;
break;
case 'g':
growable = 1;
break;
case 'k':
flags |= BDRV_O_NATIVE_AIO;
break;
case 't':
if (bdrv_parse_cache_flags(optarg, &flags) < 0) {
error_report("Invalid cache option: %s", optarg);
exit(1);
}
break;
case 'T':
if (!trace_backend_init(optarg, NULL)) {
exit(1); /* error message will have been printed */
}
break;
case 'V':
printf("%s version %s\n", progname, VERSION);
exit(0);
case 'h':
usage(progname);
exit(0);
default:
usage(progname);
exit(1);
}
}
if ((argc - optind) > 1) {
usage(progname);
exit(1);
}
qemu_init_main_loop();
bdrv_init();
/* initialize commands */
quit_init();
help_init();
add_command(&open_cmd);
add_command(&close_cmd);
add_command(&read_cmd);
add_command(&readv_cmd);
add_command(&write_cmd);
add_command(&writev_cmd);
add_command(&multiwrite_cmd);
add_command(&aio_read_cmd);
add_command(&aio_write_cmd);
add_command(&aio_flush_cmd);
add_command(&flush_cmd);
add_command(&truncate_cmd);
add_command(&length_cmd);
add_command(&info_cmd);
add_command(&discard_cmd);
add_command(&alloc_cmd);
add_command(&map_cmd);
add_command(&break_cmd);
add_command(&resume_cmd);
add_command(&wait_break_cmd);
add_command(&abort_cmd);
add_args_command(init_args_command);
add_check_command(init_check_command);
/* open the device */
if (!readonly) {
flags |= BDRV_O_RDWR;
}
if ((argc - optind) == 1) {
openfile(argv[optind], flags, growable);
}
command_loop();
/*
* Make sure all outstanding requests complete before the program exits.
*/
bdrv_drain_all();
if (bs) {
bdrv_delete(bs);
}
return 0;
}
static int aio_flush_f(int argc, char **argv)
{
bdrv_drain_all();
return 0;
}
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, sectors_per_chunk, length;
uint64_t last_pause_ns;
BlockDriverInfo bdi;
char backing_filename[1024];
int ret = 0;
int n;
if (block_job_is_cancelled(&s->common)) {
goto immediate_exit;
}
s->common.len = bdrv_getlength(bs);
if (s->common.len <= 0) {
block_job_completed(&s->common, s->common.len);
return;
}
length = (bdrv_getlength(bs) + s->granularity - 1) / s->granularity;
s->in_flight_bitmap = bitmap_new(length);
/* If we have no backing file yet in the destination, we cannot let
* the destination do COW. Instead, we copy sectors around the
* dirty data if needed. We need a bitmap to do that.
*/
bdrv_get_backing_filename(s->target, backing_filename,
sizeof(backing_filename));
if (backing_filename[0] && !s->target->backing_hd) {
bdrv_get_info(s->target, &bdi);
if (s->granularity < bdi.cluster_size) {
s->buf_size = MAX(s->buf_size, bdi.cluster_size);
s->cow_bitmap = bitmap_new(length);
}
}
end = s->common.len >> BDRV_SECTOR_BITS;
s->buf = qemu_blockalign(bs, s->buf_size);
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
mirror_free_init(s);
if (s->mode != MIRROR_SYNC_MODE_NONE) {
/* First part, loop on the sectors and initialize the dirty bitmap. */
BlockDriverState *base;
base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
for (sector_num = 0; sector_num < end; ) {
int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
ret = bdrv_is_allocated_above(bs, base,
sector_num, next - sector_num, &n);
if (ret < 0) {
goto immediate_exit;
}
assert(n > 0);
if (ret == 1) {
bdrv_set_dirty(bs, sector_num, n);
sector_num = next;
} else {
sector_num += n;
}
}
}
bdrv_dirty_iter_init(bs, &s->hbi);
last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
for (;;) {
uint64_t delay_ns;
int64_t cnt;
bool should_complete;
if (s->ret < 0) {
ret = s->ret;
goto immediate_exit;
}
cnt = bdrv_get_dirty_count(bs);
/* Note that even when no rate limit is applied we need to yield
* periodically with no pending I/O so that qemu_aio_flush() returns.
* We do so every SLICE_TIME nanoseconds, or when there is an error,
* or when the source is clean, whichever comes first.
*/
if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - last_pause_ns < SLICE_TIME &&
s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
(cnt == 0 && s->in_flight > 0)) {
trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
qemu_coroutine_yield();
continue;
} else if (cnt != 0) {
mirror_iteration(s);
continue;
}
}
should_complete = false;
if (s->in_flight == 0 && cnt == 0) {
trace_mirror_before_flush(s);
ret = bdrv_flush(s->target);
if (ret < 0) {
if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
goto immediate_exit;
}
} else {
/* We're out of the streaming phase. From now on, if the job
* is cancelled we will actually complete all pending I/O and
* report completion. This way, block-job-cancel will leave
* the target in a consistent state.
*/
s->common.offset = end * BDRV_SECTOR_SIZE;
if (!s->synced) {
block_job_ready(&s->common);
s->synced = true;
}
should_complete = s->should_complete ||
block_job_is_cancelled(&s->common);
cnt = bdrv_get_dirty_count(bs);
}
}
if (cnt == 0 && should_complete) {
/* The dirty bitmap is not updated while operations are pending.
* If we're about to exit, wait for pending operations before
* calling bdrv_get_dirty_count(bs), or we may exit while the
* source has dirty data to copy!
*
* Note that I/O can be submitted by the guest while
* mirror_populate runs.
*/
trace_mirror_before_drain(s, cnt);
bdrv_drain_all();
cnt = bdrv_get_dirty_count(bs);
}
ret = 0;
trace_mirror_before_sleep(s, cnt, s->synced);
if (!s->synced) {
/* Publish progress */
s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
if (s->common.speed) {
delay_ns = ratelimit_calculate_delay(&s->limit, sectors_per_chunk);
} else {
delay_ns = 0;
}
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
if (block_job_is_cancelled(&s->common)) {
break;
}
} else if (!should_complete) {
delay_ns = (s->in_flight == 0 && cnt == 0 ? SLICE_TIME : 0);
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
} else if (cnt == 0) {
/* The two disks are in sync. Exit and report successful
* completion.
*/
assert(QLIST_EMPTY(&bs->tracked_requests));
s->common.cancelled = false;
break;
}
last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
}
immediate_exit:
if (s->in_flight > 0) {
/* We get here only if something went wrong. Either the job failed,
* or it was cancelled prematurely so that we do not guarantee that
* the target is a copy of the source.
*/
assert(ret < 0 || (!s->synced && block_job_is_cancelled(&s->common)));
mirror_drain(s);
}
assert(s->in_flight == 0);
qemu_vfree(s->buf);
g_free(s->cow_bitmap);
g_free(s->in_flight_bitmap);
bdrv_set_dirty_tracking(bs, 0);
bdrv_iostatus_disable(s->target);
if (s->should_complete && ret == 0) {
if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
}
bdrv_swap(s->target, s->common.bs);
}
bdrv_close(s->target);
bdrv_unref(s->target);
block_job_completed(&s->common, ret);
}
int main(int argc, char **argv)
{
int readonly = 0;
int growable = 0;
const char *sopt = "hVc:Crsnmgk";
struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "offset", 1, NULL, 'o' },
{ "cmd", 1, NULL, 'c' },
{ "create", 0, NULL, 'C' },
{ "read-only", 0, NULL, 'r' },
{ "snapshot", 0, NULL, 's' },
{ "nocache", 0, NULL, 'n' },
{ "misalign", 0, NULL, 'm' },
{ "growable", 0, NULL, 'g' },
{ "native-aio", 0, NULL, 'k' },
{ NULL, 0, NULL, 0 }
};
int c;
int opt_index = 0;
int flags = 0;
progname = basename(argv[0]);
while ((c = getopt_long(argc, argv, sopt, lopt, &opt_index)) != -1) {
switch (c) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
break;
case 'c':
add_user_command(optarg);
break;
case 'C':
flags |= BDRV_O_CREAT;
break;
case 'r':
readonly = 1;
break;
case 'm':
misalign = 1;
break;
case 'g':
growable = 1;
break;
case 'k':
flags |= BDRV_O_NATIVE_AIO;
break;
case 'V':
printf("%s version %s\n", progname, VERSION);
exit(0);
case 'h':
usage(progname);
exit(0);
default:
usage(progname);
exit(1);
}
}
if ((argc - optind) > 1) {
usage(progname);
exit(1);
}
bdrv_init();
/* initialize commands */
quit_init();
help_init();
add_command(&open_cmd);
add_command(&close_cmd);
add_command(&read_cmd);
add_command(&readv_cmd);
add_command(&write_cmd);
add_command(&writev_cmd);
add_command(&aio_read_cmd);
add_command(&aio_write_cmd);
add_command(&aio_flush_cmd);
add_command(&flush_cmd);
add_command(&truncate_cmd);
add_command(&length_cmd);
add_command(&info_cmd);
add_command(&alloc_cmd);
add_args_command(init_args_command);
add_check_command(init_check_command);
/* open the device */
if (!readonly) {
flags |= BDRV_O_RDWR;
}
if ((argc - optind) == 1) {
openfile(argv[optind], flags, growable);
}
command_loop();
/*
* Make sure all outstanding requests complete before the program exits.
*/
bdrv_drain_all();
if (bs) {
bdrv_close(bs);
}
return 0;
}
int main(int argc, char **argv)
{
int readonly = 0;
int growable = 0;
const char *sopt = "hVc:d:rsnmgkt:T:";
const struct option lopt[] = {
{ "help", 0, NULL, 'h' },
{ "version", 0, NULL, 'V' },
{ "offset", 1, NULL, 'o' },
{ "cmd", 1, NULL, 'c' },
{ "read-only", 0, NULL, 'r' },
{ "snapshot", 0, NULL, 's' },
{ "nocache", 0, NULL, 'n' },
{ "misalign", 0, NULL, 'm' },
{ "growable", 0, NULL, 'g' },
{ "native-aio", 0, NULL, 'k' },
{ "discard", 1, NULL, 'd' },
{ "cache", 1, NULL, 't' },
{ "trace", 1, NULL, 'T' },
{ NULL, 0, NULL, 0 }
};
int c;
int opt_index = 0;
int flags = BDRV_O_UNMAP;
#ifdef CONFIG_POSIX
signal(SIGPIPE, SIG_IGN);
#endif
progname = basename(argv[0]);
while ((c = getopt_long(argc, argv, sopt, lopt, &opt_index)) != -1) {
switch (c) {
case 's':
flags |= BDRV_O_SNAPSHOT;
break;
case 'n':
flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
break;
case 'd':
if (bdrv_parse_discard_flags(optarg, &flags) < 0) {
error_report("Invalid discard option: %s", optarg);
exit(1);
}
break;
case 'c':
add_user_command(optarg);
break;
case 'r':
readonly = 1;
break;
case 'm':
qemuio_misalign = 1;
break;
case 'g':
growable = 1;
break;
case 'k':
flags |= BDRV_O_NATIVE_AIO;
break;
case 't':
if (bdrv_parse_cache_flags(optarg, &flags) < 0) {
error_report("Invalid cache option: %s", optarg);
exit(1);
}
break;
case 'T':
if (!trace_backend_init(optarg, NULL)) {
exit(1); /* error message will have been printed */
}
break;
case 'V':
printf("%s version %s\n", progname, QEMU_VERSION);
exit(0);
case 'h':
usage(progname);
exit(0);
default:
usage(progname);
exit(1);
}
}
if ((argc - optind) > 1) {
usage(progname);
exit(1);
}
qemu_init_main_loop();
bdrv_init();
/* initialize commands */
qemuio_add_command(&quit_cmd);
qemuio_add_command(&open_cmd);
qemuio_add_command(&close_cmd);
if (isatty(STDIN_FILENO)) {
readline_state = readline_init(readline_printf_func,
readline_flush_func,
NULL,
readline_completion_func);
qemu_set_tty_echo(STDIN_FILENO, false);
atexit(reenable_tty_echo);
}
/* open the device */
if (!readonly) {
flags |= BDRV_O_RDWR;
}
if ((argc - optind) == 1) {
openfile(argv[optind], flags, growable, NULL);
}
command_loop();
/*
* Make sure all outstanding requests complete before the program exits.
*/
bdrv_drain_all();
if (qemuio_bs) {
bdrv_unref(qemuio_bs);
}
g_free(readline_state);
return 0;
}
