static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
int64_t sector_num, int nb_sectors);
-static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
- bool is_write, double elapsed_time, uint64_t *wait);
-static bool bdrv_exceed_iops_limits(BlockDriverState *bs, bool is_write,
- double elapsed_time, uint64_t *wait);
-static bool bdrv_exceed_io_limits(BlockDriverState *bs, int nb_sectors,
- bool is_write, int64_t *wait);
-
static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
QTAILQ_HEAD_INITIALIZER(bdrv_states);
static QLIST_HEAD(, BlockDriver) bdrv_drivers =
QLIST_HEAD_INITIALIZER(bdrv_drivers);
-/* The device to use for VM snapshots */
-static BlockDriverState *bs_snapshots;
-
/* If non-zero, use only whitelisted block drivers */
static int use_bdrv_whitelist;
#endif
/* throttling disk I/O limits */
-void bdrv_io_limits_disable(BlockDriverState *bs)
+void bdrv_set_io_limits(BlockDriverState *bs,
+ ThrottleConfig *cfg)
{
- bs->io_limits_enabled = false;
+ int i;
+
+ throttle_config(&bs->throttle_state, cfg);
+
+ for (i = 0; i < 2; i++) {
+ qemu_co_enter_next(&bs->throttled_reqs[i]);
+ }
+}
+
+/* this function drain all the throttled IOs */
+static bool bdrv_start_throttled_reqs(BlockDriverState *bs)
+{
+ bool drained = false;
+ bool enabled = bs->io_limits_enabled;
+ int i;
- while (qemu_co_queue_next(&bs->throttled_reqs));
+ bs->io_limits_enabled = false;
- if (bs->block_timer) {
- qemu_del_timer(bs->block_timer);
- qemu_free_timer(bs->block_timer);
- bs->block_timer = NULL;
+ for (i = 0; i < 2; i++) {
+ while (qemu_co_enter_next(&bs->throttled_reqs[i])) {
+ drained = true;
+ }
}
- bs->slice_start = 0;
- bs->slice_end = 0;
- bs->slice_time = 0;
- memset(&bs->io_base, 0, sizeof(bs->io_base));
+ bs->io_limits_enabled = enabled;
+
+ return drained;
}
-static void bdrv_block_timer(void *opaque)
+void bdrv_io_limits_disable(BlockDriverState *bs)
{
- BlockDriverState *bs = opaque;
+ bs->io_limits_enabled = false;
- qemu_co_queue_next(&bs->throttled_reqs);
+ bdrv_start_throttled_reqs(bs);
+
+ throttle_destroy(&bs->throttle_state);
}
-void bdrv_io_limits_enable(BlockDriverState *bs)
+static void bdrv_throttle_read_timer_cb(void *opaque)
{
- qemu_co_queue_init(&bs->throttled_reqs);
- bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
- bs->io_limits_enabled = true;
+ BlockDriverState *bs = opaque;
+ qemu_co_enter_next(&bs->throttled_reqs[0]);
}
-bool bdrv_io_limits_enabled(BlockDriverState *bs)
+static void bdrv_throttle_write_timer_cb(void *opaque)
{
- BlockIOLimit *io_limits = &bs->io_limits;
- return io_limits->bps[BLOCK_IO_LIMIT_READ]
- || io_limits->bps[BLOCK_IO_LIMIT_WRITE]
- || io_limits->bps[BLOCK_IO_LIMIT_TOTAL]
- || io_limits->iops[BLOCK_IO_LIMIT_READ]
- || io_limits->iops[BLOCK_IO_LIMIT_WRITE]
- || io_limits->iops[BLOCK_IO_LIMIT_TOTAL];
+ BlockDriverState *bs = opaque;
+ qemu_co_enter_next(&bs->throttled_reqs[1]);
+}
+
+/* should be called before bdrv_set_io_limits if a limit is set */
+void bdrv_io_limits_enable(BlockDriverState *bs)
+{
+ assert(!bs->io_limits_enabled);
+ throttle_init(&bs->throttle_state,
+ QEMU_CLOCK_VIRTUAL,
+ bdrv_throttle_read_timer_cb,
+ bdrv_throttle_write_timer_cb,
+ bs);
+ bs->io_limits_enabled = true;
}
+/* This function makes an IO wait if needed
+ *
+ * @nb_sectors: the number of sectors of the IO
+ * @is_write: is the IO a write
+ */
static void bdrv_io_limits_intercept(BlockDriverState *bs,
- bool is_write, int nb_sectors)
+ int nb_sectors,
+ bool is_write)
{
- int64_t wait_time = -1;
+ /* does this io must wait */
+ bool must_wait = throttle_schedule_timer(&bs->throttle_state, is_write);
- if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
- qemu_co_queue_wait(&bs->throttled_reqs);
+ /* if must wait or any request of this type throttled queue the IO */
+ if (must_wait ||
+ !qemu_co_queue_empty(&bs->throttled_reqs[is_write])) {
+ qemu_co_queue_wait(&bs->throttled_reqs[is_write]);
}
- /* In fact, we hope to keep each request's timing, in FIFO mode. The next
- * throttled requests will not be dequeued until the current request is
- * allowed to be serviced. So if the current request still exceeds the
- * limits, it will be inserted to the head. All requests followed it will
- * be still in throttled_reqs queue.
- */
+ /* the IO will be executed, do the accounting */
+ throttle_account(&bs->throttle_state,
+ is_write,
+ nb_sectors * BDRV_SECTOR_SIZE);
- while (bdrv_exceed_io_limits(bs, nb_sectors, is_write, &wait_time)) {
- qemu_mod_timer(bs->block_timer,
- wait_time + qemu_get_clock_ns(vm_clock));
- qemu_co_queue_wait_insert_head(&bs->throttled_reqs);
+ /* if the next request must wait -> do nothing */
+ if (throttle_schedule_timer(&bs->throttle_state, is_write)) {
+ return;
}
- qemu_co_queue_next(&bs->throttled_reqs);
+ /* else queue next request for execution */
+ qemu_co_queue_next(&bs->throttled_reqs[is_write]);
}
/* check if the path starts with "<protocol>:" */
}
bdrv_iostatus_disable(bs);
notifier_list_init(&bs->close_notifiers);
+ notifier_with_return_list_init(&bs->before_write_notifiers);
+ qemu_co_queue_init(&bs->throttled_reqs[0]);
+ qemu_co_queue_init(&bs->throttled_reqs[1]);
+ bs->refcnt = 1;
return bs;
}
return NULL;
}
-static int bdrv_is_whitelisted(BlockDriver *drv)
+static int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
{
- static const char *whitelist[] = {
- CONFIG_BDRV_WHITELIST
+ static const char *whitelist_rw[] = {
+ CONFIG_BDRV_RW_WHITELIST
+ };
+ static const char *whitelist_ro[] = {
+ CONFIG_BDRV_RO_WHITELIST
};
const char **p;
- if (!whitelist[0])
+ if (!whitelist_rw[0] && !whitelist_ro[0]) {
return 1; /* no whitelist, anything goes */
+ }
- for (p = whitelist; *p; p++) {
+ for (p = whitelist_rw; *p; p++) {
if (!strcmp(drv->format_name, *p)) {
return 1;
}
}
+ if (read_only) {
+ for (p = whitelist_ro; *p; p++) {
+ if (!strcmp(drv->format_name, *p)) {
+ return 1;
+ }
+ }
+ }
return 0;
}
-BlockDriver *bdrv_find_whitelisted_format(const char *format_name)
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
+ bool read_only)
{
BlockDriver *drv = bdrv_find_format(format_name);
- return drv && bdrv_is_whitelisted(drv) ? drv : NULL;
+ return drv && bdrv_is_whitelisted(drv, read_only) ? drv : NULL;
}
typedef struct CreateCo {
char *filename;
QEMUOptionParameter *options;
int ret;
+ Error *err;
} CreateCo;
static void coroutine_fn bdrv_create_co_entry(void *opaque)
{
+ Error *local_err = NULL;
+ int ret;
+
CreateCo *cco = opaque;
assert(cco->drv);
- cco->ret = cco->drv->bdrv_create(cco->filename, cco->options);
+ ret = cco->drv->bdrv_create(cco->filename, cco->options, &local_err);
+ if (error_is_set(&local_err)) {
+ error_propagate(&cco->err, local_err);
+ }
+ cco->ret = ret;
}
int bdrv_create(BlockDriver *drv, const char* filename,
- QEMUOptionParameter *options)
+ QEMUOptionParameter *options, Error **errp)
{
int ret;
.filename = g_strdup(filename),
.options = options,
.ret = NOT_DONE,
+ .err = NULL,
};
if (!drv->bdrv_create) {
+ error_setg(errp, "Driver '%s' does not support image creation", drv->format_name);
ret = -ENOTSUP;
goto out;
}
}
ret = cco.ret;
+ if (ret < 0) {
+ if (error_is_set(&cco.err)) {
+ error_propagate(errp, cco.err);
+ } else {
+ error_setg_errno(errp, -ret, "Could not create image");
+ }
+ }
out:
g_free(cco.filename);
return ret;
}
-int bdrv_create_file(const char* filename, QEMUOptionParameter *options)
+int bdrv_create_file(const char* filename, QEMUOptionParameter *options,
+ Error **errp)
{
BlockDriver *drv;
+ Error *local_err = NULL;
+ int ret;
- drv = bdrv_find_protocol(filename);
+ drv = bdrv_find_protocol(filename, true);
if (drv == NULL) {
+ error_setg(errp, "Could not find protocol for file '%s'", filename);
return -ENOENT;
}
- return bdrv_create(drv, filename, options);
+ ret = bdrv_create(drv, filename, options, &local_err);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ }
+ return ret;
}
/*
return drv;
}
-BlockDriver *bdrv_find_protocol(const char *filename)
+BlockDriver *bdrv_find_protocol(const char *filename,
+ bool allow_protocol_prefix)
{
BlockDriver *drv1;
char protocol[128];
return drv1;
}
- if (!path_has_protocol(filename)) {
+ if (!path_has_protocol(filename) || !allow_protocol_prefix) {
return bdrv_find_format("file");
}
+
p = strchr(filename, ':');
assert(p != NULL);
len = p - filename;
}
static int find_image_format(BlockDriverState *bs, const char *filename,
- BlockDriver **pdrv)
+ BlockDriver **pdrv, Error **errp)
{
int score, score_max;
BlockDriver *drv1, *drv;
if (bs->sg || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
drv = bdrv_find_format("raw");
if (!drv) {
+ error_setg(errp, "Could not find raw image format");
ret = -ENOENT;
}
*pdrv = drv;
ret = bdrv_pread(bs, 0, buf, sizeof(buf));
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not read image for determining its "
+ "format");
*pdrv = NULL;
return ret;
}
}
}
if (!drv) {
+ error_setg(errp, "Could not determine image format: No compatible "
+ "driver found");
ret = -ENOENT;
}
*pdrv = drv;
* Removes all processed options from *options.
*/
static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
- const char *filename, QDict *options,
- int flags, BlockDriver *drv)
+ QDict *options, int flags, BlockDriver *drv, Error **errp)
{
int ret, open_flags;
+ const char *filename;
+ Error *local_err = NULL;
assert(drv != NULL);
assert(bs->file == NULL);
- assert(options == NULL || bs->options != options);
+ assert(options != NULL && bs->options != options);
+
+ if (file != NULL) {
+ filename = file->filename;
+ } else {
+ filename = qdict_get_try_str(options, "filename");
+ }
- trace_bdrv_open_common(bs, filename, flags, drv->format_name);
+ trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
+
+ /* bdrv_open() with directly using a protocol as drv. This layer is already
+ * opened, so assign it to bs (while file becomes a closed BlockDriverState)
+ * and return immediately. */
+ if (file != NULL && drv->bdrv_file_open) {
+ bdrv_swap(file, bs);
+ return 0;
+ }
bs->open_flags = flags;
bs->buffer_alignment = 512;
+ bs->zero_beyond_eof = true;
+ open_flags = bdrv_open_flags(bs, flags);
+ bs->read_only = !(open_flags & BDRV_O_RDWR);
+
+ if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
+ error_setg(errp, "Driver '%s' is not whitelisted", drv->format_name);
+ return -ENOTSUP;
+ }
assert(bs->copy_on_read == 0); /* bdrv_new() and bdrv_close() make it so */
- if ((flags & BDRV_O_RDWR) && (flags & BDRV_O_COPY_ON_READ)) {
+ if (!bs->read_only && (flags & BDRV_O_COPY_ON_READ)) {
bdrv_enable_copy_on_read(bs);
}
- pstrcpy(bs->filename, sizeof(bs->filename), filename);
-
- if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv)) {
- return -ENOTSUP;
+ if (filename != NULL) {
+ pstrcpy(bs->filename, sizeof(bs->filename), filename);
+ } else {
+ bs->filename[0] = '\0';
}
bs->drv = drv;
bs->opaque = g_malloc0(drv->instance_size);
bs->enable_write_cache = !!(flags & BDRV_O_CACHE_WB);
- open_flags = bdrv_open_flags(bs, flags);
-
- bs->read_only = !(open_flags & BDRV_O_RDWR);
/* Open the image, either directly or using a protocol */
if (drv->bdrv_file_open) {
- if (file != NULL) {
- bdrv_swap(file, bs);
- ret = 0;
- } else {
- ret = drv->bdrv_file_open(bs, filename, open_flags);
- }
+ assert(file == NULL);
+ assert(!drv->bdrv_needs_filename || filename != NULL);
+ ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
} else {
- assert(file != NULL);
+ if (file == NULL) {
+ error_setg(errp, "Can't use '%s' as a block driver for the "
+ "protocol level", drv->format_name);
+ ret = -EINVAL;
+ goto free_and_fail;
+ }
bs->file = file;
- ret = drv->bdrv_open(bs, options, open_flags);
+ ret = drv->bdrv_open(bs, options, open_flags, &local_err);
}
if (ret < 0) {
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ } else if (filename) {
+ error_setg_errno(errp, -ret, "Could not open '%s'", filename);
+ } else {
+ error_setg_errno(errp, -ret, "Could not open image");
+ }
goto free_and_fail;
}
ret = refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not refresh total sector count");
goto free_and_fail;
}
#ifndef _WIN32
if (bs->is_temporary) {
+ assert(filename != NULL);
unlink(filename);
}
#endif
/*
* Opens a file using a protocol (file, host_device, nbd, ...)
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict belongs to the block layer
+ * after the call (even on failure), so if the caller intends to reuse the
+ * dictionary, it needs to use QINCREF() before calling bdrv_file_open.
*/
-int bdrv_file_open(BlockDriverState **pbs, const char *filename, int flags)
+int bdrv_file_open(BlockDriverState **pbs, const char *filename,
+ QDict *options, int flags, Error **errp)
{
BlockDriverState *bs;
BlockDriver *drv;
+ const char *drvname;
+ bool allow_protocol_prefix = false;
+ Error *local_err = NULL;
int ret;
- drv = bdrv_find_protocol(filename);
- if (!drv) {
- return -ENOENT;
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
}
bs = bdrv_new("");
- ret = bdrv_open_common(bs, NULL, filename, NULL, flags, drv);
+ bs->options = options;
+ options = qdict_clone_shallow(options);
+
+ /* Fetch the file name from the options QDict if necessary */
+ if (!filename) {
+ filename = qdict_get_try_str(options, "filename");
+ } else if (filename && !qdict_haskey(options, "filename")) {
+ qdict_put(options, "filename", qstring_from_str(filename));
+ allow_protocol_prefix = true;
+ } else {
+ error_setg(errp, "Can't specify 'file' and 'filename' options at the "
+ "same time");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ /* Find the right block driver */
+ drvname = qdict_get_try_str(options, "driver");
+ if (drvname) {
+ drv = bdrv_find_whitelisted_format(drvname, !(flags & BDRV_O_RDWR));
+ if (!drv) {
+ error_setg(errp, "Unknown driver '%s'", drvname);
+ }
+ qdict_del(options, "driver");
+ } else if (filename) {
+ drv = bdrv_find_protocol(filename, allow_protocol_prefix);
+ if (!drv) {
+ error_setg(errp, "Unknown protocol");
+ }
+ } else {
+ error_setg(errp, "Must specify either driver or file");
+ drv = NULL;
+ }
+
+ if (!drv) {
+ /* errp has been set already */
+ ret = -ENOENT;
+ goto fail;
+ }
+
+ /* Parse the filename and open it */
+ if (drv->bdrv_parse_filename && filename) {
+ drv->bdrv_parse_filename(filename, options, &local_err);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ ret = -EINVAL;
+ goto fail;
+ }
+ qdict_del(options, "filename");
+ } else if (drv->bdrv_needs_filename && !filename) {
+ error_setg(errp, "The '%s' block driver requires a file name",
+ drv->format_name);
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ ret = bdrv_open_common(bs, NULL, options, flags, drv, &local_err);
if (ret < 0) {
- bdrv_delete(bs);
- return ret;
+ error_propagate(errp, local_err);
+ goto fail;
}
+
+ /* Check if any unknown options were used */
+ if (qdict_size(options) != 0) {
+ const QDictEntry *entry = qdict_first(options);
+ error_setg(errp, "Block protocol '%s' doesn't support the option '%s'",
+ drv->format_name, entry->key);
+ ret = -EINVAL;
+ goto fail;
+ }
+ QDECREF(options);
+
bs->growable = 1;
*pbs = bs;
return 0;
+
+fail:
+ QDECREF(options);
+ if (!bs->drv) {
+ QDECREF(bs->options);
+ }
+ bdrv_unref(bs);
+ return ret;
}
-int bdrv_open_backing_file(BlockDriverState *bs)
+/*
+ * Opens the backing file for a BlockDriverState if not yet open
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict is transferred to this
+ * function (even on failure), so if the caller intends to reuse the dictionary,
+ * it needs to use QINCREF() before calling bdrv_file_open.
+ */
+int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
{
char backing_filename[PATH_MAX];
int back_flags, ret;
BlockDriver *back_drv = NULL;
+ Error *local_err = NULL;
if (bs->backing_hd != NULL) {
+ QDECREF(options);
return 0;
}
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
bs->open_flags &= ~BDRV_O_NO_BACKING;
- if (bs->backing_file[0] == '\0') {
+ if (qdict_haskey(options, "file.filename")) {
+ backing_filename[0] = '\0';
+ } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
+ QDECREF(options);
return 0;
+ } else {
+ bdrv_get_full_backing_filename(bs, backing_filename,
+ sizeof(backing_filename));
}
bs->backing_hd = bdrv_new("");
- bdrv_get_full_backing_filename(bs, backing_filename,
- sizeof(backing_filename));
if (bs->backing_format[0] != '\0') {
back_drv = bdrv_find_format(bs->backing_format);
/* backing files always opened read-only */
back_flags = bs->open_flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT);
- ret = bdrv_open(bs->backing_hd, backing_filename, NULL,
- back_flags, back_drv);
+ ret = bdrv_open(bs->backing_hd,
+ *backing_filename ? backing_filename : NULL, options,
+ back_flags, back_drv, &local_err);
+ pstrcpy(bs->backing_file, sizeof(bs->backing_file),
+ bs->backing_hd->file->filename);
if (ret < 0) {
- bdrv_delete(bs->backing_hd);
+ bdrv_unref(bs->backing_hd);
bs->backing_hd = NULL;
bs->open_flags |= BDRV_O_NO_BACKING;
+ error_propagate(errp, local_err);
return ret;
}
return 0;
* dictionary, it needs to use QINCREF() before calling bdrv_open.
*/
int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
- int flags, BlockDriver *drv)
+ int flags, BlockDriver *drv, Error **errp)
{
int ret;
/* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
char tmp_filename[PATH_MAX + 1];
BlockDriverState *file = NULL;
+ QDict *file_options = NULL;
+ const char *drvname;
+ Error *local_err = NULL;
/* NULL means an empty set of options */
if (options == NULL) {
BlockDriverState *bs1;
int64_t total_size;
BlockDriver *bdrv_qcow2;
- QEMUOptionParameter *options;
+ QEMUOptionParameter *create_options;
char backing_filename[PATH_MAX];
+ if (qdict_size(options) != 0) {
+ error_setg(errp, "Can't use snapshot=on with driver-specific options");
+ ret = -EINVAL;
+ goto fail;
+ }
+ assert(filename != NULL);
+
/* if snapshot, we create a temporary backing file and open it
instead of opening 'filename' directly */
/* if there is a backing file, use it */
bs1 = bdrv_new("");
- ret = bdrv_open(bs1, filename, NULL, 0, drv);
+ ret = bdrv_open(bs1, filename, NULL, 0, drv, &local_err);
if (ret < 0) {
- bdrv_delete(bs1);
+ bdrv_unref(bs1);
goto fail;
}
total_size = bdrv_getlength(bs1) & BDRV_SECTOR_MASK;
- bdrv_delete(bs1);
+ bdrv_unref(bs1);
ret = get_tmp_filename(tmp_filename, sizeof(tmp_filename));
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not get temporary filename");
goto fail;
}
snprintf(backing_filename, sizeof(backing_filename),
"%s", filename);
} else if (!realpath(filename, backing_filename)) {
+ error_setg_errno(errp, errno, "Could not resolve path '%s'", filename);
ret = -errno;
goto fail;
}
bdrv_qcow2 = bdrv_find_format("qcow2");
- options = parse_option_parameters("", bdrv_qcow2->create_options, NULL);
+ create_options = parse_option_parameters("", bdrv_qcow2->create_options,
+ NULL);
- set_option_parameter_int(options, BLOCK_OPT_SIZE, total_size);
- set_option_parameter(options, BLOCK_OPT_BACKING_FILE, backing_filename);
+ set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
+ set_option_parameter(create_options, BLOCK_OPT_BACKING_FILE,
+ backing_filename);
if (drv) {
- set_option_parameter(options, BLOCK_OPT_BACKING_FMT,
+ set_option_parameter(create_options, BLOCK_OPT_BACKING_FMT,
drv->format_name);
}
- ret = bdrv_create(bdrv_qcow2, tmp_filename, options);
- free_option_parameters(options);
+ ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options, &local_err);
+ free_option_parameters(create_options);
if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not create temporary overlay "
+ "'%s': %s", tmp_filename,
+ error_get_pretty(local_err));
+ error_free(local_err);
+ local_err = NULL;
goto fail;
}
flags |= BDRV_O_ALLOW_RDWR;
}
- ret = bdrv_file_open(&file, filename, bdrv_open_flags(bs, flags));
+ qdict_extract_subqdict(options, &file_options, "file.");
+
+ ret = bdrv_file_open(&file, filename, file_options,
+ bdrv_open_flags(bs, flags | BDRV_O_UNMAP), &local_err);
if (ret < 0) {
goto fail;
}
/* Find the right image format driver */
+ drvname = qdict_get_try_str(options, "driver");
+ if (drvname) {
+ drv = bdrv_find_whitelisted_format(drvname, !(flags & BDRV_O_RDWR));
+ qdict_del(options, "driver");
+ }
+
if (!drv) {
- ret = find_image_format(file, filename, &drv);
+ ret = find_image_format(file, filename, &drv, &local_err);
}
if (!drv) {
}
/* Open the image */
- ret = bdrv_open_common(bs, file, filename, options, flags, drv);
+ ret = bdrv_open_common(bs, file, options, flags, drv, &local_err);
if (ret < 0) {
goto unlink_and_fail;
}
if (bs->file != file) {
- bdrv_delete(file);
+ bdrv_unref(file);
file = NULL;
}
/* If there is a backing file, use it */
if ((flags & BDRV_O_NO_BACKING) == 0) {
- ret = bdrv_open_backing_file(bs);
+ QDict *backing_options;
+
+ qdict_extract_subqdict(options, &backing_options, "backing.");
+ ret = bdrv_open_backing_file(bs, backing_options, &local_err);
if (ret < 0) {
goto close_and_fail;
}
/* Check if any unknown options were used */
if (qdict_size(options) != 0) {
const QDictEntry *entry = qdict_first(options);
- qerror_report(ERROR_CLASS_GENERIC_ERROR, "Block format '%s' used by "
- "device '%s' doesn't support the option '%s'",
- drv->format_name, bs->device_name, entry->key);
+ error_setg(errp, "Block format '%s' used by device '%s' doesn't "
+ "support the option '%s'", drv->format_name, bs->device_name,
+ entry->key);
ret = -EINVAL;
goto close_and_fail;
bdrv_dev_change_media_cb(bs, true);
}
- /* throttling disk I/O limits */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_enable(bs);
- }
-
return 0;
unlink_and_fail:
if (file != NULL) {
- bdrv_delete(file);
+ bdrv_unref(file);
}
if (bs->is_temporary) {
unlink(filename);
QDECREF(bs->options);
QDECREF(options);
bs->options = NULL;
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ }
return ret;
close_and_fail:
bdrv_close(bs);
QDECREF(options);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ }
return ret;
}
if (local_err != NULL) {
error_propagate(errp, local_err);
} else {
- error_set(errp, QERR_OPEN_FILE_FAILED,
- reopen_state->bs->filename);
+ error_setg(errp, "failed while preparing to reopen image '%s'",
+ reopen_state->bs->filename);
}
goto error;
}
void bdrv_close(BlockDriverState *bs)
{
- bdrv_flush(bs);
if (bs->job) {
block_job_cancel_sync(bs->job);
}
- bdrv_drain_all();
+ bdrv_drain_all(); /* complete I/O */
+ bdrv_flush(bs);
+ bdrv_drain_all(); /* in case flush left pending I/O */
notifier_list_notify(&bs->close_notifiers, bs);
if (bs->drv) {
- if (bs == bs_snapshots) {
- bs_snapshots = NULL;
- }
if (bs->backing_hd) {
- bdrv_delete(bs->backing_hd);
+ bdrv_unref(bs->backing_hd);
bs->backing_hd = NULL;
}
bs->drv->bdrv_close(bs);
bs->valid_key = 0;
bs->sg = 0;
bs->growable = 0;
+ bs->zero_beyond_eof = false;
QDECREF(bs->options);
bs->options = NULL;
if (bs->file != NULL) {
- bdrv_delete(bs->file);
+ bdrv_unref(bs->file);
bs->file = NULL;
}
}
}
}
+/* Check if any requests are in-flight (including throttled requests) */
+static bool bdrv_requests_pending(BlockDriverState *bs)
+{
+ if (!QLIST_EMPTY(&bs->tracked_requests)) {
+ return true;
+ }
+ if (!qemu_co_queue_empty(&bs->throttled_reqs[0])) {
+ return true;
+ }
+ if (!qemu_co_queue_empty(&bs->throttled_reqs[1])) {
+ return true;
+ }
+ if (bs->file && bdrv_requests_pending(bs->file)) {
+ return true;
+ }
+ if (bs->backing_hd && bdrv_requests_pending(bs->backing_hd)) {
+ return true;
+ }
+ return false;
+}
+
+static bool bdrv_requests_pending_all(void)
+{
+ BlockDriverState *bs;
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (bdrv_requests_pending(bs)) {
+ return true;
+ }
+ }
+ return false;
+}
+
/*
* Wait for pending requests to complete across all BlockDriverStates
*
*/
void bdrv_drain_all(void)
{
+ /* Always run first iteration so any pending completion BHs run */
+ bool busy = true;
BlockDriverState *bs;
- bool busy;
-
- do {
- busy = qemu_aio_wait();
+ while (busy) {
/* FIXME: We do not have timer support here, so this is effectively
* a busy wait.
*/
QTAILQ_FOREACH(bs, &bdrv_states, list) {
- if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
- qemu_co_queue_restart_all(&bs->throttled_reqs);
+ if (bdrv_start_throttled_reqs(bs)) {
busy = true;
}
}
- } while (busy);
- /* If requests are still pending there is a bug somewhere */
- QTAILQ_FOREACH(bs, &bdrv_states, list) {
- assert(QLIST_EMPTY(&bs->tracked_requests));
- assert(qemu_co_queue_empty(&bs->throttled_reqs));
+ busy = bdrv_requests_pending_all();
+ busy |= aio_poll(qemu_get_aio_context(), busy);
}
}
bs_dest->enable_write_cache = bs_src->enable_write_cache;
- /* i/o timing parameters */
- bs_dest->slice_time = bs_src->slice_time;
- bs_dest->slice_start = bs_src->slice_start;
- bs_dest->slice_end = bs_src->slice_end;
- bs_dest->io_limits = bs_src->io_limits;
- bs_dest->io_base = bs_src->io_base;
- bs_dest->throttled_reqs = bs_src->throttled_reqs;
- bs_dest->block_timer = bs_src->block_timer;
+ /* i/o throttled req */
+ memcpy(&bs_dest->throttle_state,
+ &bs_src->throttle_state,
+ sizeof(ThrottleState));
+ bs_dest->throttled_reqs[0] = bs_src->throttled_reqs[0];
+ bs_dest->throttled_reqs[1] = bs_src->throttled_reqs[1];
bs_dest->io_limits_enabled = bs_src->io_limits_enabled;
/* r/w error */
/* dirty bitmap */
bs_dest->dirty_bitmap = bs_src->dirty_bitmap;
+ /* reference count */
+ bs_dest->refcnt = bs_src->refcnt;
+
/* job */
bs_dest->in_use = bs_src->in_use;
bs_dest->job = bs_src->job;
assert(bs_new->dev == NULL);
assert(bs_new->in_use == 0);
assert(bs_new->io_limits_enabled == false);
- assert(bs_new->block_timer == NULL);
+ assert(!throttle_have_timer(&bs_new->throttle_state));
tmp = *bs_new;
*bs_new = *bs_old;
assert(bs_new->job == NULL);
assert(bs_new->in_use == 0);
assert(bs_new->io_limits_enabled == false);
- assert(bs_new->block_timer == NULL);
+ assert(!throttle_have_timer(&bs_new->throttle_state));
bdrv_rebind(bs_new);
bdrv_rebind(bs_old);
bs_new->drv ? bs_new->drv->format_name : "");
}
-void bdrv_delete(BlockDriverState *bs)
+static void bdrv_delete(BlockDriverState *bs)
{
assert(!bs->dev);
assert(!bs->job);
assert(!bs->in_use);
+ assert(!bs->refcnt);
+
+ bdrv_close(bs);
/* remove from list, if necessary */
bdrv_make_anon(bs);
- bdrv_close(bs);
-
- assert(bs != bs_snapshots);
g_free(bs);
}
{
bs->dev_ops = ops;
bs->dev_opaque = opaque;
- if (bdrv_dev_has_removable_media(bs) && bs == bs_snapshots) {
- bs_snapshots = NULL;
- }
}
void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
buf = g_malloc(COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE);
for (sector = 0; sector < total_sectors; sector += n) {
- if (bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n)) {
-
+ ret = bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n);
+ if (ret < 0) {
+ goto ro_cleanup;
+ }
+ if (ret) {
if (bdrv_read(bs, sector, buf, n) != 0) {
ret = -EIO;
goto ro_cleanup;
return 0;
}
-struct BdrvTrackedRequest {
- BlockDriverState *bs;
- int64_t sector_num;
- int nb_sectors;
- bool is_write;
- QLIST_ENTRY(BdrvTrackedRequest) list;
- Coroutine *co; /* owner, used for deadlock detection */
- CoQueue wait_queue; /* coroutines blocked on this request */
-};
-
/**
* Remove an active request from the tracked requests list
*
QSIMPLEQ_FOREACH_SAFE(intermediate_state, &states_to_delete, entry, next) {
/* so that bdrv_close() does not recursively close the chain */
intermediate_state->bs->backing_hd = NULL;
- bdrv_delete(intermediate_state->bs);
+ bdrv_unref(intermediate_state->bs);
}
ret = 0;
QEMUIOVector *qiov;
bool is_write;
int ret;
+ BdrvRequestFlags flags;
} RwCo;
static void coroutine_fn bdrv_rw_co_entry(void *opaque)
if (!rwco->is_write) {
rwco->ret = bdrv_co_do_readv(rwco->bs, rwco->sector_num,
- rwco->nb_sectors, rwco->qiov, 0);
+ rwco->nb_sectors, rwco->qiov,
+ rwco->flags);
} else {
rwco->ret = bdrv_co_do_writev(rwco->bs, rwco->sector_num,
- rwco->nb_sectors, rwco->qiov, 0);
+ rwco->nb_sectors, rwco->qiov,
+ rwco->flags);
}
}
/*
- * Process a synchronous request using coroutines
+ * Process a vectored synchronous request using coroutines
*/
-static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
- int nb_sectors, bool is_write)
+static int bdrv_rwv_co(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, bool is_write,
+ BdrvRequestFlags flags)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
- };
Coroutine *co;
RwCo rwco = {
.bs = bs,
.sector_num = sector_num,
- .nb_sectors = nb_sectors,
- .qiov = &qiov,
+ .nb_sectors = qiov->size >> BDRV_SECTOR_BITS,
+ .qiov = qiov,
.is_write = is_write,
.ret = NOT_DONE,
+ .flags = flags,
};
-
- qemu_iovec_init_external(&qiov, &iov, 1);
+ assert((qiov->size & (BDRV_SECTOR_SIZE - 1)) == 0);
/**
* In sync call context, when the vcpu is blocked, this throttling timer
return rwco.ret;
}
+/*
+ * Process a synchronous request using coroutines
+ */
+static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
+ int nb_sectors, bool is_write, BdrvRequestFlags flags)
+{
+ QEMUIOVector qiov;
+ struct iovec iov = {
+ .iov_base = (void *)buf,
+ .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
+ };
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ return bdrv_rwv_co(bs, sector_num, &qiov, is_write, flags);
+}
+
/* return < 0 if error. See bdrv_write() for the return codes */
int bdrv_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
- return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false);
+ return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false, 0);
}
/* Just like bdrv_read(), but with I/O throttling temporarily disabled */
enabled = bs->io_limits_enabled;
bs->io_limits_enabled = false;
- ret = bdrv_read(bs, 0, buf, 1);
+ ret = bdrv_read(bs, sector_num, buf, nb_sectors);
bs->io_limits_enabled = enabled;
return ret;
}
int bdrv_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
- return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true);
+ return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true, 0);
+}
+
+int bdrv_writev(BlockDriverState *bs, int64_t sector_num, QEMUIOVector *qiov)
+{
+ return bdrv_rwv_co(bs, sector_num, qiov, true, 0);
+}
+
+int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
+{
+ return bdrv_rw_co(bs, sector_num, NULL, nb_sectors, true,
+ BDRV_REQ_ZERO_WRITE);
}
int bdrv_pread(BlockDriverState *bs, int64_t offset,
return count1;
}
-int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
- const void *buf, int count1)
+int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
{
uint8_t tmp_buf[BDRV_SECTOR_SIZE];
int len, nb_sectors, count;
int64_t sector_num;
int ret;
- count = count1;
+ count = qiov->size;
+
/* first write to align to sector start */
len = (BDRV_SECTOR_SIZE - offset) & (BDRV_SECTOR_SIZE - 1);
if (len > count)
if (len > 0) {
if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
return ret;
- memcpy(tmp_buf + (offset & (BDRV_SECTOR_SIZE - 1)), buf, len);
+ qemu_iovec_to_buf(qiov, 0, tmp_buf + (offset & (BDRV_SECTOR_SIZE - 1)),
+ len);
if ((ret = bdrv_write(bs, sector_num, tmp_buf, 1)) < 0)
return ret;
count -= len;
if (count == 0)
- return count1;
+ return qiov->size;
sector_num++;
- buf += len;
}
/* write the sectors "in place" */
nb_sectors = count >> BDRV_SECTOR_BITS;
if (nb_sectors > 0) {
- if ((ret = bdrv_write(bs, sector_num, buf, nb_sectors)) < 0)
+ QEMUIOVector qiov_inplace;
+
+ qemu_iovec_init(&qiov_inplace, qiov->niov);
+ qemu_iovec_concat(&qiov_inplace, qiov, len,
+ nb_sectors << BDRV_SECTOR_BITS);
+ ret = bdrv_writev(bs, sector_num, &qiov_inplace);
+ qemu_iovec_destroy(&qiov_inplace);
+ if (ret < 0) {
return ret;
+ }
+
sector_num += nb_sectors;
len = nb_sectors << BDRV_SECTOR_BITS;
- buf += len;
count -= len;
}
if (count > 0) {
if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
return ret;
- memcpy(tmp_buf, buf, count);
+ qemu_iovec_to_buf(qiov, qiov->size - count, tmp_buf, count);
if ((ret = bdrv_write(bs, sector_num, tmp_buf, 1)) < 0)
return ret;
}
- return count1;
+ return qiov->size;
}
-/*
- * Writes to the file and ensures that no writes are reordered across this
- * request (acts as a barrier)
- *
- * Returns 0 on success, -errno in error cases.
- */
+int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
+ const void *buf, int count1)
+{
+ QEMUIOVector qiov;
+ struct iovec iov = {
+ .iov_base = (void *) buf,
+ .iov_len = count1,
+ };
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ return bdrv_pwritev(bs, offset, &qiov);
+}
+
+/*
+ * Writes to the file and ensures that no writes are reordered across this
+ * request (acts as a barrier)
+ *
+ * Returns 0 on success, -errno in error cases.
+ */
int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
const void *buf, int count)
{
return -EIO;
}
- /* throttling disk read I/O */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_intercept(bs, false, nb_sectors);
- }
-
if (bs->copy_on_read) {
flags |= BDRV_REQ_COPY_ON_READ;
}
wait_for_overlapping_requests(bs, sector_num, nb_sectors);
}
+ /* throttling disk I/O */
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_intercept(bs, nb_sectors, false);
+ }
+
tracked_request_begin(&req, bs, sector_num, nb_sectors, false);
if (flags & BDRV_REQ_COPY_ON_READ) {
int pnum;
- ret = bdrv_co_is_allocated(bs, sector_num, nb_sectors, &pnum);
+ ret = bdrv_is_allocated(bs, sector_num, nb_sectors, &pnum);
if (ret < 0) {
goto out;
}
}
}
- ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+ if (!(bs->zero_beyond_eof && bs->growable)) {
+ ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+ } else {
+ /* Read zeros after EOF of growable BDSes */
+ int64_t len, total_sectors, max_nb_sectors;
+
+ len = bdrv_getlength(bs);
+ if (len < 0) {
+ ret = len;
+ goto out;
+ }
+
+ total_sectors = DIV_ROUND_UP(len, BDRV_SECTOR_SIZE);
+ max_nb_sectors = MAX(0, total_sectors - sector_num);
+ if (max_nb_sectors > 0) {
+ ret = drv->bdrv_co_readv(bs, sector_num,
+ MIN(nb_sectors, max_nb_sectors), qiov);
+ } else {
+ ret = 0;
+ }
+
+ /* Reading beyond end of file is supposed to produce zeroes */
+ if (ret == 0 && total_sectors < sector_num + nb_sectors) {
+ uint64_t offset = MAX(0, total_sectors - sector_num);
+ uint64_t bytes = (sector_num + nb_sectors - offset) *
+ BDRV_SECTOR_SIZE;
+ qemu_iovec_memset(qiov, offset * BDRV_SECTOR_SIZE, 0, bytes);
+ }
+ }
out:
tracked_request_end(&req);
return -EIO;
}
- /* throttling disk write I/O */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_intercept(bs, true, nb_sectors);
- }
-
if (bs->copy_on_read_in_flight) {
wait_for_overlapping_requests(bs, sector_num, nb_sectors);
}
+ /* throttling disk I/O */
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_intercept(bs, nb_sectors, true);
+ }
+
tracked_request_begin(&req, bs, sector_num, nb_sectors, true);
- if (flags & BDRV_REQ_ZERO_WRITE) {
+ ret = notifier_with_return_list_notify(&bs->before_write_notifiers, &req);
+
+ if (ret < 0) {
+ /* Do nothing, write notifier decided to fail this request */
+ } else if (flags & BDRV_REQ_ZERO_WRITE) {
ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors);
} else {
ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
bs->wr_highest_sector = sector_num + nb_sectors - 1;
}
+ if (bs->growable && ret >= 0) {
+ bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
+ }
tracked_request_end(&req);
if (!drv)
return -ENOMEDIUM;
- if (bs->growable || bdrv_dev_has_removable_media(bs)) {
+ if (bdrv_dev_has_removable_media(bs)) {
if (drv->bdrv_getlength) {
return drv->bdrv_getlength(bs);
}
*nb_sectors_ptr = length;
}
-/* throttling disk io limits */
-void bdrv_set_io_limits(BlockDriverState *bs,
- BlockIOLimit *io_limits)
-{
- bs->io_limits = *io_limits;
- bs->io_limits_enabled = bdrv_io_limits_enabled(bs);
-}
-
void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
BlockdevOnError on_write_error)
{
return bs->open_flags;
}
-void bdrv_flush_all(void)
+int bdrv_flush_all(void)
{
BlockDriverState *bs;
+ int result = 0;
QTAILQ_FOREACH(bs, &bdrv_states, list) {
- bdrv_flush(bs);
+ int ret = bdrv_flush(bs);
+ if (ret < 0 && !result) {
+ result = ret;
+ }
}
+
+ return result;
+}
+
+int bdrv_has_zero_init_1(BlockDriverState *bs)
+{
+ return 1;
}
int bdrv_has_zero_init(BlockDriverState *bs)
{
assert(bs->drv);
+ /* If BS is a copy on write image, it is initialized to
+ the contents of the base image, which may not be zeroes. */
+ if (bs->backing_hd) {
+ return 0;
+ }
if (bs->drv->bdrv_has_zero_init) {
return bs->drv->bdrv_has_zero_init(bs);
}
- return 1;
+ /* safe default */
+ return 0;
}
-typedef struct BdrvCoIsAllocatedData {
+typedef struct BdrvCoGetBlockStatusData {
BlockDriverState *bs;
BlockDriverState *base;
int64_t sector_num;
int nb_sectors;
int *pnum;
- int ret;
+ int64_t ret;
bool done;
-} BdrvCoIsAllocatedData;
+} BdrvCoGetBlockStatusData;
/*
* Returns true iff the specified sector is present in the disk image. Drivers
* 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
* beyond the end of the disk image it will be clamped.
*/
-int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, int *pnum)
+static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
+ int64_t sector_num,
+ int nb_sectors, int *pnum)
{
+ int64_t length;
int64_t n;
+ int64_t ret, ret2;
+
+ length = bdrv_getlength(bs);
+ if (length < 0) {
+ return length;
+ }
- if (sector_num >= bs->total_sectors) {
+ if (sector_num >= (length >> BDRV_SECTOR_BITS)) {
*pnum = 0;
return 0;
}
nb_sectors = n;
}
- if (!bs->drv->bdrv_co_is_allocated) {
+ if (!bs->drv->bdrv_co_get_block_status) {
*pnum = nb_sectors;
- return 1;
+ ret = BDRV_BLOCK_DATA;
+ if (bs->drv->protocol_name) {
+ ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE);
+ }
+ return ret;
}
- return bs->drv->bdrv_co_is_allocated(bs, sector_num, nb_sectors, pnum);
+ ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum);
+ if (ret < 0) {
+ *pnum = 0;
+ return ret;
+ }
+
+ if (!(ret & BDRV_BLOCK_DATA)) {
+ if (bdrv_has_zero_init(bs)) {
+ ret |= BDRV_BLOCK_ZERO;
+ } else if (bs->backing_hd) {
+ BlockDriverState *bs2 = bs->backing_hd;
+ int64_t length2 = bdrv_getlength(bs2);
+ if (length2 >= 0 && sector_num >= (length2 >> BDRV_SECTOR_BITS)) {
+ ret |= BDRV_BLOCK_ZERO;
+ }
+ }
+ }
+
+ if (bs->file &&
+ (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) &&
+ (ret & BDRV_BLOCK_OFFSET_VALID)) {
+ ret2 = bdrv_co_get_block_status(bs->file, ret >> BDRV_SECTOR_BITS,
+ *pnum, pnum);
+ if (ret2 >= 0) {
+ /* Ignore errors. This is just providing extra information, it
+ * is useful but not necessary.
+ */
+ ret |= (ret2 & BDRV_BLOCK_ZERO);
+ }
+ }
+
+ return ret;
}
-/* Coroutine wrapper for bdrv_is_allocated() */
-static void coroutine_fn bdrv_is_allocated_co_entry(void *opaque)
+/* Coroutine wrapper for bdrv_get_block_status() */
+static void coroutine_fn bdrv_get_block_status_co_entry(void *opaque)
{
- BdrvCoIsAllocatedData *data = opaque;
+ BdrvCoGetBlockStatusData *data = opaque;
BlockDriverState *bs = data->bs;
- data->ret = bdrv_co_is_allocated(bs, data->sector_num, data->nb_sectors,
- data->pnum);
+ data->ret = bdrv_co_get_block_status(bs, data->sector_num, data->nb_sectors,
+ data->pnum);
data->done = true;
}
/*
- * Synchronous wrapper around bdrv_co_is_allocated().
+ * Synchronous wrapper around bdrv_co_get_block_status().
*
- * See bdrv_co_is_allocated() for details.
+ * See bdrv_co_get_block_status() for details.
*/
-int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
- int *pnum)
+int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, int *pnum)
{
Coroutine *co;
- BdrvCoIsAllocatedData data = {
+ BdrvCoGetBlockStatusData data = {
.bs = bs,
.sector_num = sector_num,
.nb_sectors = nb_sectors,
.done = false,
};
- co = qemu_coroutine_create(bdrv_is_allocated_co_entry);
- qemu_coroutine_enter(co, &data);
- while (!data.done) {
- qemu_aio_wait();
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_get_block_status_co_entry(&data);
+ } else {
+ co = qemu_coroutine_create(bdrv_get_block_status_co_entry);
+ qemu_coroutine_enter(co, &data);
+ while (!data.done) {
+ qemu_aio_wait();
+ }
}
return data.ret;
}
+int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, int *pnum)
+{
+ int64_t ret = bdrv_get_block_status(bs, sector_num, nb_sectors, pnum);
+ if (ret < 0) {
+ return ret;
+ }
+ return
+ (ret & BDRV_BLOCK_DATA) ||
+ ((ret & BDRV_BLOCK_ZERO) && !bdrv_has_zero_init(bs));
+}
+
/*
* Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP]
*
* allocated/unallocated state.
*
*/
-int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top,
- BlockDriverState *base,
- int64_t sector_num,
- int nb_sectors, int *pnum)
+int bdrv_is_allocated_above(BlockDriverState *top,
+ BlockDriverState *base,
+ int64_t sector_num,
+ int nb_sectors, int *pnum)
{
BlockDriverState *intermediate;
int ret, n = nb_sectors;
intermediate = top;
while (intermediate && intermediate != base) {
int pnum_inter;
- ret = bdrv_co_is_allocated(intermediate, sector_num, nb_sectors,
- &pnum_inter);
+ ret = bdrv_is_allocated(intermediate, sector_num, nb_sectors,
+ &pnum_inter);
if (ret < 0) {
return ret;
} else if (ret) {
return 0;
}
-/* Coroutine wrapper for bdrv_is_allocated_above() */
-static void coroutine_fn bdrv_is_allocated_above_co_entry(void *opaque)
-{
- BdrvCoIsAllocatedData *data = opaque;
- BlockDriverState *top = data->bs;
- BlockDriverState *base = data->base;
-
- data->ret = bdrv_co_is_allocated_above(top, base, data->sector_num,
- data->nb_sectors, data->pnum);
- data->done = true;
-}
-
-/*
- * Synchronous wrapper around bdrv_co_is_allocated_above().
- *
- * See bdrv_co_is_allocated_above() for details.
- */
-int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
- int64_t sector_num, int nb_sectors, int *pnum)
-{
- Coroutine *co;
- BdrvCoIsAllocatedData data = {
- .bs = top,
- .base = base,
- .sector_num = sector_num,
- .nb_sectors = nb_sectors,
- .pnum = pnum,
- .done = false,
- };
-
- co = qemu_coroutine_create(bdrv_is_allocated_above_co_entry);
- qemu_coroutine_enter(co, &data);
- while (!data.done) {
- qemu_aio_wait();
- }
- return data.ret;
-}
-
-BlockInfo *bdrv_query_info(BlockDriverState *bs)
-{
- BlockInfo *info = g_malloc0(sizeof(*info));
- info->device = g_strdup(bs->device_name);
- info->type = g_strdup("unknown");
- info->locked = bdrv_dev_is_medium_locked(bs);
- info->removable = bdrv_dev_has_removable_media(bs);
-
- if (bdrv_dev_has_removable_media(bs)) {
- info->has_tray_open = true;
- info->tray_open = bdrv_dev_is_tray_open(bs);
- }
-
- if (bdrv_iostatus_is_enabled(bs)) {
- info->has_io_status = true;
- info->io_status = bs->iostatus;
- }
-
- if (bs->dirty_bitmap) {
- info->has_dirty = true;
- info->dirty = g_malloc0(sizeof(*info->dirty));
- info->dirty->count = bdrv_get_dirty_count(bs) * BDRV_SECTOR_SIZE;
- info->dirty->granularity =
- ((int64_t) BDRV_SECTOR_SIZE << hbitmap_granularity(bs->dirty_bitmap));
- }
-
- if (bs->drv) {
- info->has_inserted = true;
- info->inserted = g_malloc0(sizeof(*info->inserted));
- info->inserted->file = g_strdup(bs->filename);
- info->inserted->ro = bs->read_only;
- info->inserted->drv = g_strdup(bs->drv->format_name);
- info->inserted->encrypted = bs->encrypted;
- info->inserted->encryption_key_missing = bdrv_key_required(bs);
-
- if (bs->backing_file[0]) {
- info->inserted->has_backing_file = true;
- info->inserted->backing_file = g_strdup(bs->backing_file);
- }
-
- info->inserted->backing_file_depth = bdrv_get_backing_file_depth(bs);
-
- if (bs->io_limits_enabled) {
- info->inserted->bps =
- bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL];
- info->inserted->bps_rd =
- bs->io_limits.bps[BLOCK_IO_LIMIT_READ];
- info->inserted->bps_wr =
- bs->io_limits.bps[BLOCK_IO_LIMIT_WRITE];
- info->inserted->iops =
- bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL];
- info->inserted->iops_rd =
- bs->io_limits.iops[BLOCK_IO_LIMIT_READ];
- info->inserted->iops_wr =
- bs->io_limits.iops[BLOCK_IO_LIMIT_WRITE];
- }
- }
- return info;
-}
-
-BlockInfoList *qmp_query_block(Error **errp)
-{
- BlockInfoList *head = NULL, **p_next = &head;
- BlockDriverState *bs;
-
- QTAILQ_FOREACH(bs, &bdrv_states, list) {
- BlockInfoList *info = g_malloc0(sizeof(*info));
- info->value = bdrv_query_info(bs);
-
- *p_next = info;
- p_next = &info->next;
- }
-
- return head;
-}
-
-BlockStats *bdrv_query_stats(const BlockDriverState *bs)
-{
- BlockStats *s;
-
- s = g_malloc0(sizeof(*s));
-
- if (bs->device_name[0]) {
- s->has_device = true;
- s->device = g_strdup(bs->device_name);
- }
-
- s->stats = g_malloc0(sizeof(*s->stats));
- s->stats->rd_bytes = bs->nr_bytes[BDRV_ACCT_READ];
- s->stats->wr_bytes = bs->nr_bytes[BDRV_ACCT_WRITE];
- s->stats->rd_operations = bs->nr_ops[BDRV_ACCT_READ];
- s->stats->wr_operations = bs->nr_ops[BDRV_ACCT_WRITE];
- s->stats->wr_highest_offset = bs->wr_highest_sector * BDRV_SECTOR_SIZE;
- s->stats->flush_operations = bs->nr_ops[BDRV_ACCT_FLUSH];
- s->stats->wr_total_time_ns = bs->total_time_ns[BDRV_ACCT_WRITE];
- s->stats->rd_total_time_ns = bs->total_time_ns[BDRV_ACCT_READ];
- s->stats->flush_total_time_ns = bs->total_time_ns[BDRV_ACCT_FLUSH];
-
- if (bs->file) {
- s->has_parent = true;
- s->parent = bdrv_query_stats(bs->file);
- }
-
- return s;
-}
-
-BlockStatsList *qmp_query_blockstats(Error **errp)
-{
- BlockStatsList *head = NULL, **p_next = &head;
- BlockDriverState *bs;
-
- QTAILQ_FOREACH(bs, &bdrv_states, list) {
- BlockStatsList *info = g_malloc0(sizeof(*info));
- info->value = bdrv_query_stats(bs);
-
- *p_next = info;
- p_next = &info->next;
- }
-
- return head;
-}
-
const char *bdrv_get_encrypted_filename(BlockDriverState *bs)
{
if (bs->backing_hd && bs->backing_hd->encrypted)
int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
int64_t pos, int size)
+{
+ QEMUIOVector qiov;
+ struct iovec iov = {
+ .iov_base = (void *) buf,
+ .iov_len = size,
+ };
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ return bdrv_writev_vmstate(bs, &qiov, pos);
+}
+
+int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
{
BlockDriver *drv = bs->drv;
- if (!drv)
+
+ if (!drv) {
return -ENOMEDIUM;
- if (drv->bdrv_save_vmstate)
- return drv->bdrv_save_vmstate(bs, buf, pos, size);
- if (bs->file)
- return bdrv_save_vmstate(bs->file, buf, pos, size);
+ } else if (drv->bdrv_save_vmstate) {
+ return drv->bdrv_save_vmstate(bs, qiov, pos);
+ } else if (bs->file) {
+ return bdrv_writev_vmstate(bs->file, qiov, pos);
+ }
+
return -ENOTSUP;
}
void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event)
{
- BlockDriver *drv = bs->drv;
-
- if (!drv || !drv->bdrv_debug_event) {
+ if (!bs || !bs->drv || !bs->drv->bdrv_debug_event) {
return;
}
- drv->bdrv_debug_event(bs, event);
+ bs->drv->bdrv_debug_event(bs, event);
}
int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
return false;
}
-/**************************************************************/
-/* handling of snapshots */
-
-int bdrv_can_snapshot(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
- if (!drv || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
- return 0;
- }
-
- if (!drv->bdrv_snapshot_create) {
- if (bs->file != NULL) {
- return bdrv_can_snapshot(bs->file);
- }
- return 0;
- }
-
- return 1;
-}
-
int bdrv_is_snapshot(BlockDriverState *bs)
{
return !!(bs->open_flags & BDRV_O_SNAPSHOT);
}
-BlockDriverState *bdrv_snapshots(void)
-{
- BlockDriverState *bs;
-
- if (bs_snapshots) {
- return bs_snapshots;
- }
-
- bs = NULL;
- while ((bs = bdrv_next(bs))) {
- if (bdrv_can_snapshot(bs)) {
- bs_snapshots = bs;
- return bs;
- }
- }
- return NULL;
-}
-
-int bdrv_snapshot_create(BlockDriverState *bs,
- QEMUSnapshotInfo *sn_info)
-{
- BlockDriver *drv = bs->drv;
- if (!drv)
- return -ENOMEDIUM;
- if (drv->bdrv_snapshot_create)
- return drv->bdrv_snapshot_create(bs, sn_info);
- if (bs->file)
- return bdrv_snapshot_create(bs->file, sn_info);
- return -ENOTSUP;
-}
-
-int bdrv_snapshot_goto(BlockDriverState *bs,
- const char *snapshot_id)
-{
- BlockDriver *drv = bs->drv;
- int ret, open_ret;
-
- if (!drv)
- return -ENOMEDIUM;
- if (drv->bdrv_snapshot_goto)
- return drv->bdrv_snapshot_goto(bs, snapshot_id);
-
- if (bs->file) {
- drv->bdrv_close(bs);
- ret = bdrv_snapshot_goto(bs->file, snapshot_id);
- open_ret = drv->bdrv_open(bs, NULL, bs->open_flags);
- if (open_ret < 0) {
- bdrv_delete(bs->file);
- bs->drv = NULL;
- return open_ret;
- }
- return ret;
- }
-
- return -ENOTSUP;
-}
-
-int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
-{
- BlockDriver *drv = bs->drv;
- if (!drv)
- return -ENOMEDIUM;
- if (drv->bdrv_snapshot_delete)
- return drv->bdrv_snapshot_delete(bs, snapshot_id);
- if (bs->file)
- return bdrv_snapshot_delete(bs->file, snapshot_id);
- return -ENOTSUP;
-}
-
-int bdrv_snapshot_list(BlockDriverState *bs,
- QEMUSnapshotInfo **psn_info)
-{
- BlockDriver *drv = bs->drv;
- if (!drv)
- return -ENOMEDIUM;
- if (drv->bdrv_snapshot_list)
- return drv->bdrv_snapshot_list(bs, psn_info);
- if (bs->file)
- return bdrv_snapshot_list(bs->file, psn_info);
- return -ENOTSUP;
-}
-
-int bdrv_snapshot_load_tmp(BlockDriverState *bs,
- const char *snapshot_name)
-{
- BlockDriver *drv = bs->drv;
- if (!drv) {
- return -ENOMEDIUM;
- }
- if (!bs->read_only) {
- return -EINVAL;
- }
- if (drv->bdrv_snapshot_load_tmp) {
- return drv->bdrv_snapshot_load_tmp(bs, snapshot_name);
- }
- return -ENOTSUP;
-}
-
/* backing_file can either be relative, or absolute, or a protocol. If it is
* relative, it must be relative to the chain. So, passing in bs->filename
* from a BDS as backing_file should not be done, as that may be relative to
return curr_bs;
}
-#define NB_SUFFIXES 4
-
-char *get_human_readable_size(char *buf, int buf_size, int64_t size)
-{
- static const char suffixes[NB_SUFFIXES] = "KMGT";
- int64_t base;
- int i;
-
- if (size <= 999) {
- snprintf(buf, buf_size, "%" PRId64, size);
- } else {
- base = 1024;
- for(i = 0; i < NB_SUFFIXES; i++) {
- if (size < (10 * base)) {
- snprintf(buf, buf_size, "%0.1f%c",
- (double)size / base,
- suffixes[i]);
- break;
- } else if (size < (1000 * base) || i == (NB_SUFFIXES - 1)) {
- snprintf(buf, buf_size, "%" PRId64 "%c",
- ((size + (base >> 1)) / base),
- suffixes[i]);
- break;
- }
- base = base * 1024;
- }
- }
- return buf;
-}
-
-char *bdrv_snapshot_dump(char *buf, int buf_size, QEMUSnapshotInfo *sn)
-{
- char buf1[128], date_buf[128], clock_buf[128];
- struct tm tm;
- time_t ti;
- int64_t secs;
-
- if (!sn) {
- snprintf(buf, buf_size,
- "%-10s%-20s%7s%20s%15s",
- "ID", "TAG", "VM SIZE", "DATE", "VM CLOCK");
- } else {
- ti = sn->date_sec;
- localtime_r(&ti, &tm);
- strftime(date_buf, sizeof(date_buf),
- "%Y-%m-%d %H:%M:%S", &tm);
- secs = sn->vm_clock_nsec / 1000000000;
- snprintf(clock_buf, sizeof(clock_buf),
- "%02d:%02d:%02d.%03d",
- (int)(secs / 3600),
- (int)((secs / 60) % 60),
- (int)(secs % 60),
- (int)((sn->vm_clock_nsec / 1000000) % 1000));
- snprintf(buf, buf_size,
- "%-10s%-20s%7s%20s%15s",
- sn->id_str, sn->name,
- get_human_readable_size(buf1, sizeof(buf1), sn->vm_state_size),
- date_buf,
- clock_buf);
- }
- return buf;
-}
-
/**************************************************************/
/* async I/Os */
acb->aiocb_info->cancel(acb);
}
-/* block I/O throttling */
-static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
- bool is_write, double elapsed_time, uint64_t *wait)
-{
- uint64_t bps_limit = 0;
- double bytes_limit, bytes_base, bytes_res;
- double slice_time, wait_time;
-
- if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]) {
- bps_limit = bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL];
- } else if (bs->io_limits.bps[is_write]) {
- bps_limit = bs->io_limits.bps[is_write];
- } else {
- if (wait) {
- *wait = 0;
- }
-
- return false;
- }
-
- slice_time = bs->slice_end - bs->slice_start;
- slice_time /= (NANOSECONDS_PER_SECOND);
- bytes_limit = bps_limit * slice_time;
- bytes_base = bs->nr_bytes[is_write] - bs->io_base.bytes[is_write];
- if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]) {
- bytes_base += bs->nr_bytes[!is_write] - bs->io_base.bytes[!is_write];
- }
-
- /* bytes_base: the bytes of data which have been read/written; and
- * it is obtained from the history statistic info.
- * bytes_res: the remaining bytes of data which need to be read/written.
- * (bytes_base + bytes_res) / bps_limit: used to calcuate
- * the total time for completing reading/writting all data.
- */
- bytes_res = (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
-
- if (bytes_base + bytes_res <= bytes_limit) {
- if (wait) {
- *wait = 0;
- }
-
- return false;
- }
-
- /* Calc approx time to dispatch */
- wait_time = (bytes_base + bytes_res) / bps_limit - elapsed_time;
-
- /* When the I/O rate at runtime exceeds the limits,
- * bs->slice_end need to be extended in order that the current statistic
- * info can be kept until the timer fire, so it is increased and tuned
- * based on the result of experiment.
- */
- bs->slice_time = wait_time * BLOCK_IO_SLICE_TIME * 10;
- bs->slice_end += bs->slice_time - 3 * BLOCK_IO_SLICE_TIME;
- if (wait) {
- *wait = wait_time * BLOCK_IO_SLICE_TIME * 10;
- }
-
- return true;
-}
-
-static bool bdrv_exceed_iops_limits(BlockDriverState *bs, bool is_write,
- double elapsed_time, uint64_t *wait)
-{
- uint64_t iops_limit = 0;
- double ios_limit, ios_base;
- double slice_time, wait_time;
-
- if (bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
- iops_limit = bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL];
- } else if (bs->io_limits.iops[is_write]) {
- iops_limit = bs->io_limits.iops[is_write];
- } else {
- if (wait) {
- *wait = 0;
- }
-
- return false;
- }
-
- slice_time = bs->slice_end - bs->slice_start;
- slice_time /= (NANOSECONDS_PER_SECOND);
- ios_limit = iops_limit * slice_time;
- ios_base = bs->nr_ops[is_write] - bs->io_base.ios[is_write];
- if (bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
- ios_base += bs->nr_ops[!is_write] - bs->io_base.ios[!is_write];
- }
-
- if (ios_base + 1 <= ios_limit) {
- if (wait) {
- *wait = 0;
- }
-
- return false;
- }
-
- /* Calc approx time to dispatch */
- wait_time = (ios_base + 1) / iops_limit;
- if (wait_time > elapsed_time) {
- wait_time = wait_time - elapsed_time;
- } else {
- wait_time = 0;
- }
-
- bs->slice_time = wait_time * BLOCK_IO_SLICE_TIME * 10;
- bs->slice_end += bs->slice_time - 3 * BLOCK_IO_SLICE_TIME;
- if (wait) {
- *wait = wait_time * BLOCK_IO_SLICE_TIME * 10;
- }
-
- return true;
-}
-
-static bool bdrv_exceed_io_limits(BlockDriverState *bs, int nb_sectors,
- bool is_write, int64_t *wait)
-{
- int64_t now, max_wait;
- uint64_t bps_wait = 0, iops_wait = 0;
- double elapsed_time;
- int bps_ret, iops_ret;
-
- now = qemu_get_clock_ns(vm_clock);
- if ((bs->slice_start < now)
- && (bs->slice_end > now)) {
- bs->slice_end = now + bs->slice_time;
- } else {
- bs->slice_time = 5 * BLOCK_IO_SLICE_TIME;
- bs->slice_start = now;
- bs->slice_end = now + bs->slice_time;
-
- bs->io_base.bytes[is_write] = bs->nr_bytes[is_write];
- bs->io_base.bytes[!is_write] = bs->nr_bytes[!is_write];
-
- bs->io_base.ios[is_write] = bs->nr_ops[is_write];
- bs->io_base.ios[!is_write] = bs->nr_ops[!is_write];
- }
-
- elapsed_time = now - bs->slice_start;
- elapsed_time /= (NANOSECONDS_PER_SECOND);
-
- bps_ret = bdrv_exceed_bps_limits(bs, nb_sectors,
- is_write, elapsed_time, &bps_wait);
- iops_ret = bdrv_exceed_iops_limits(bs, is_write,
- elapsed_time, &iops_wait);
- if (bps_ret || iops_ret) {
- max_wait = bps_wait > iops_wait ? bps_wait : iops_wait;
- if (wait) {
- *wait = max_wait;
- }
-
- now = qemu_get_clock_ns(vm_clock);
- if (bs->slice_end < now + max_wait) {
- bs->slice_end = now + max_wait;
- }
-
- return true;
- }
-
- if (wait) {
- *wait = 0;
- }
-
- return false;
-}
-
/**************************************************************/
/* async block device emulation */
}
/* Write back cached data to the OS even with cache=unsafe */
+ BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_OS);
if (bs->drv->bdrv_co_flush_to_os) {
ret = bs->drv->bdrv_co_flush_to_os(bs);
if (ret < 0) {
goto flush_parent;
}
+ BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
if (bs->drv->bdrv_co_flush_to_disk) {
ret = bs->drv->bdrv_co_flush_to_disk(bs);
} else if (bs->drv->bdrv_aio_flush) {
}
}
+/* Get a reference to bs */
+void bdrv_ref(BlockDriverState *bs)
+{
+ bs->refcnt++;
+}
+
+/* Release a previously grabbed reference to bs.
+ * If after releasing, reference count is zero, the BlockDriverState is
+ * deleted. */
+void bdrv_unref(BlockDriverState *bs)
+{
+ assert(bs->refcnt > 0);
+ if (--bs->refcnt == 0) {
+ bdrv_delete(bs);
+ }
+}
+
void bdrv_set_in_use(BlockDriverState *bs, int in_use)
{
assert(bs->in_use != in_use);
BlockDriverState *bs = NULL;
BlockDriver *drv, *proto_drv;
BlockDriver *backing_drv = NULL;
+ Error *local_err = NULL;
int ret = 0;
/* Find driver and parse its options */
return;
}
- proto_drv = bdrv_find_protocol(filename);
+ proto_drv = bdrv_find_protocol(filename, true);
if (!proto_drv) {
error_setg(errp, "Unknown protocol '%s'", filename);
return;
bs = bdrv_new("");
ret = bdrv_open(bs, backing_file->value.s, NULL, back_flags,
- backing_drv);
+ backing_drv, &local_err);
if (ret < 0) {
- error_setg_errno(errp, -ret, "Could not open '%s'",
- backing_file->value.s);
+ error_setg_errno(errp, -ret, "Could not open '%s': %s",
+ backing_file->value.s,
+ error_get_pretty(local_err));
+ error_free(local_err);
+ local_err = NULL;
goto out;
}
bdrv_get_geometry(bs, &size);
print_option_parameters(param);
puts("");
}
- ret = bdrv_create(drv, filename, param);
- if (ret < 0) {
- if (ret == -ENOTSUP) {
- error_setg(errp,"Formatting or formatting option not supported for "
- "file format '%s'", fmt);
- } else if (ret == -EFBIG) {
- error_setg(errp, "The image size is too large for file format '%s'",
- fmt);
- } else {
- error_setg(errp, "%s: error while creating %s: %s", filename, fmt,
- strerror(-ret));
+ ret = bdrv_create(drv, filename, param, &local_err);
+ if (ret == -EFBIG) {
+ /* This is generally a better message than whatever the driver would
+ * deliver (especially because of the cluster_size_hint), since that
+ * is most probably not much different from "image too large". */
+ const char *cluster_size_hint = "";
+ if (get_option_parameter(create_options, BLOCK_OPT_CLUSTER_SIZE)) {
+ cluster_size_hint = " (try using a larger cluster size)";
}
+ error_setg(errp, "The image size is too large for file format '%s'"
+ "%s", fmt, cluster_size_hint);
+ error_free(local_err);
+ local_err = NULL;
}
out:
free_option_parameters(param);
if (bs) {
- bdrv_delete(bs);
+ bdrv_unref(bs);
+ }
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
}
}
/* Currently BlockDriverState always uses the main loop AioContext */
return qemu_get_aio_context();
}
+
+void bdrv_add_before_write_notifier(BlockDriverState *bs,
+ NotifierWithReturn *notifier)
+{
+ notifier_with_return_list_add(&bs->before_write_notifiers, notifier);
+}
+
+int bdrv_amend_options(BlockDriverState *bs, QEMUOptionParameter *options)
+{
+ if (bs->drv->bdrv_amend_options == NULL) {
+ return -ENOTSUP;
+ }
+ return bs->drv->bdrv_amend_options(bs, options);
+}