static QLIST_HEAD(, BlockDriver) bdrv_drivers =
QLIST_HEAD_INITIALIZER(bdrv_drivers);
-static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
- const char *reference, QDict *options, int flags,
- BlockDriverState *parent,
- const BdrvChildRole *child_role, Error **errp);
+static BlockDriverState *bdrv_open_inherit(const char *filename,
+ const char *reference,
+ QDict *options, int flags,
+ BlockDriverState *parent,
+ const BdrvChildRole *child_role,
+ Error **errp);
/* If non-zero, use only whitelisted block drivers */
static int use_bdrv_whitelist;
-static void bdrv_close(BlockDriverState *bs);
-
#ifdef _WIN32
static int is_windows_drive_prefix(const char *filename)
{
QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
}
-BlockDriverState *bdrv_new_root(void)
-{
- return bdrv_new();
-}
-
BlockDriverState *bdrv_new(void)
{
BlockDriverState *bs;
return 0;
}
+static void bdrv_child_cb_drained_begin(BdrvChild *child)
+{
+ BlockDriverState *bs = child->opaque;
+ bdrv_drained_begin(bs);
+}
+
+static void bdrv_child_cb_drained_end(BdrvChild *child)
+{
+ BlockDriverState *bs = child->opaque;
+ bdrv_drained_end(bs);
+}
+
/*
* Returns the options and flags that a temporary snapshot should get, based on
* the originally requested flags (the originally requested image will have
/* For temporary files, unconditional cache=unsafe is fine */
qdict_set_default_str(child_options, BDRV_OPT_CACHE_DIRECT, "off");
qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on");
+
+ /* aio=native doesn't work for cache.direct=off, so disable it for the
+ * temporary snapshot */
+ *child_flags &= ~BDRV_O_NATIVE_AIO;
}
/*
const BdrvChildRole child_file = {
.inherit_options = bdrv_inherited_options,
+ .drained_begin = bdrv_child_cb_drained_begin,
+ .drained_end = bdrv_child_cb_drained_end,
};
/*
const BdrvChildRole child_format = {
.inherit_options = bdrv_inherited_fmt_options,
+ .drained_begin = bdrv_child_cb_drained_begin,
+ .drained_end = bdrv_child_cb_drained_end,
};
/*
static const BdrvChildRole child_backing = {
.inherit_options = bdrv_backing_options,
+ .drained_begin = bdrv_child_cb_drained_begin,
+ .drained_end = bdrv_child_cb_drained_end,
};
static int bdrv_open_flags(BlockDriverState *bs, int flags)
goto fail_opts;
}
- bs->request_alignment = 512;
- bs->zero_beyond_eof = true;
+ bs->request_alignment = drv->bdrv_co_preadv ? 1 : 512;
bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
assert(bdrv_opt_mem_align(bs) != 0);
assert(bdrv_min_mem_align(bs) != 0);
- assert((bs->request_alignment != 0) || bdrv_is_sg(bs));
+ assert(is_power_of_2(bs->request_alignment) || bdrv_is_sg(bs));
qemu_opts_del(opts);
return 0;
return 0;
}
+static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
+{
+ BlockDriverState *old_bs = child->bs;
+
+ if (old_bs) {
+ if (old_bs->quiesce_counter && child->role->drained_end) {
+ child->role->drained_end(child);
+ }
+ QLIST_REMOVE(child, next_parent);
+ }
+
+ child->bs = new_bs;
+
+ if (new_bs) {
+ QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
+ if (new_bs->quiesce_counter && child->role->drained_begin) {
+ child->role->drained_begin(child);
+ }
+ }
+}
+
BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
const char *child_name,
- const BdrvChildRole *child_role)
+ const BdrvChildRole *child_role,
+ void *opaque)
{
BdrvChild *child = g_new(BdrvChild, 1);
*child = (BdrvChild) {
- .bs = child_bs,
+ .bs = NULL,
.name = g_strdup(child_name),
.role = child_role,
+ .opaque = opaque,
};
- QLIST_INSERT_HEAD(&child_bs->parents, child, next_parent);
+ bdrv_replace_child(child, child_bs);
return child;
}
const char *child_name,
const BdrvChildRole *child_role)
{
- BdrvChild *child = bdrv_root_attach_child(child_bs, child_name, child_role);
+ BdrvChild *child = bdrv_root_attach_child(child_bs, child_name, child_role,
+ parent_bs);
QLIST_INSERT_HEAD(&parent_bs->children, child, next);
return child;
}
QLIST_REMOVE(child, next);
child->next.le_prev = NULL;
}
- QLIST_REMOVE(child, next_parent);
+
+ bdrv_replace_child(child, NULL);
+
g_free(child->name);
g_free(child);
}
bdrv_root_unref_child(child);
}
+
+static void bdrv_parent_cb_change_media(BlockDriverState *bs, bool load)
+{
+ BdrvChild *c;
+ QLIST_FOREACH(c, &bs->parents, next_parent) {
+ if (c->role->change_media) {
+ c->role->change_media(c, load);
+ }
+ }
+}
+
+static void bdrv_parent_cb_resize(BlockDriverState *bs)
+{
+ BdrvChild *c;
+ QLIST_FOREACH(c, &bs->parents, next_parent) {
+ if (c->role->resize) {
+ c->role->resize(c);
+ }
+ }
+}
+
/*
* Sets the backing file link of a BDS. A new reference is created; callers
* which don't need their own reference any more must call bdrv_unref().
qdict_put(options, "driver", qstring_from_str(bs->backing_format));
}
- backing_hd = NULL;
- ret = bdrv_open_inherit(&backing_hd,
- *backing_filename ? backing_filename : NULL,
- reference, options, 0, bs, &child_backing,
- errp);
- if (ret < 0) {
+ backing_hd = bdrv_open_inherit(*backing_filename ? backing_filename : NULL,
+ reference, options, 0, bs, &child_backing,
+ errp);
+ if (!backing_hd) {
bs->open_flags |= BDRV_O_NO_BACKING;
error_prepend(errp, "Could not open backing file: ");
+ ret = -EINVAL;
goto free_exit;
}
BdrvChild *c = NULL;
BlockDriverState *bs;
QDict *image_options;
- int ret;
char *bdref_key_dot;
const char *reference;
goto done;
}
- bs = NULL;
- ret = bdrv_open_inherit(&bs, filename, reference, image_options, 0,
- parent, child_role, errp);
- if (ret < 0) {
+ bs = bdrv_open_inherit(filename, reference, image_options, 0,
+ parent, child_role, errp);
+ if (!bs) {
goto done;
}
return c;
}
-static int bdrv_append_temp_snapshot(BlockDriverState *bs, int flags,
- QDict *snapshot_options, Error **errp)
+static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
+ int flags,
+ QDict *snapshot_options,
+ Error **errp)
{
/* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
char *tmp_filename = g_malloc0(PATH_MAX + 1);
int64_t total_size;
QemuOpts *opts = NULL;
BlockDriverState *bs_snapshot;
- Error *local_err = NULL;
int ret;
/* if snapshot, we create a temporary backing file and open it
/* Get the required size from the image */
total_size = bdrv_getlength(bs);
if (total_size < 0) {
- ret = total_size;
error_setg_errno(errp, -total_size, "Could not get image size");
goto out;
}
qdict_put(snapshot_options, "driver",
qstring_from_str("qcow2"));
- bs_snapshot = bdrv_new();
-
- ret = bdrv_open(&bs_snapshot, NULL, NULL, snapshot_options,
- flags, &local_err);
+ bs_snapshot = bdrv_open(NULL, NULL, snapshot_options, flags, errp);
snapshot_options = NULL;
- if (ret < 0) {
- error_propagate(errp, local_err);
+ if (!bs_snapshot) {
+ ret = -EINVAL;
goto out;
}
+ /* bdrv_append() consumes a strong reference to bs_snapshot (i.e. it will
+ * call bdrv_unref() on it), so in order to be able to return one, we have
+ * to increase bs_snapshot's refcount here */
+ bdrv_ref(bs_snapshot);
bdrv_append(bs_snapshot, bs);
+ g_free(tmp_filename);
+ return bs_snapshot;
+
out:
QDECREF(snapshot_options);
g_free(tmp_filename);
- return ret;
+ return NULL;
}
/*
* should be opened. If specified, neither options nor a filename may be given,
* nor can an existing BDS be reused (that is, *pbs has to be NULL).
*/
-static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
- const char *reference, QDict *options, int flags,
- BlockDriverState *parent,
- const BdrvChildRole *child_role, Error **errp)
+static BlockDriverState *bdrv_open_inherit(const char *filename,
+ const char *reference,
+ QDict *options, int flags,
+ BlockDriverState *parent,
+ const BdrvChildRole *child_role,
+ Error **errp)
{
int ret;
BdrvChild *file = NULL;
QDict *snapshot_options = NULL;
int snapshot_flags = 0;
- assert(pbs);
assert(!child_role || !flags);
assert(!child_role == !parent);
bool options_non_empty = options ? qdict_size(options) : false;
QDECREF(options);
- if (*pbs) {
- error_setg(errp, "Cannot reuse an existing BDS when referencing "
- "another block device");
- return -EINVAL;
- }
-
if (filename || options_non_empty) {
error_setg(errp, "Cannot reference an existing block device with "
"additional options or a new filename");
- return -EINVAL;
+ return NULL;
}
bs = bdrv_lookup_bs(reference, reference, errp);
if (!bs) {
- return -ENODEV;
- }
-
- if (bs->blk && blk_get_public(bs->blk)->throttle_state) {
- error_setg(errp, "Cannot reference an existing block device for "
- "which I/O throttling is enabled");
- return -EINVAL;
+ return NULL;
}
bdrv_ref(bs);
- *pbs = bs;
- return 0;
+ return bs;
}
- if (*pbs) {
- bs = *pbs;
- } else {
- bs = bdrv_new();
- }
+ bs = bdrv_new();
/* NULL means an empty set of options */
if (options == NULL) {
/* json: syntax counts as explicit options, as if in the QDict */
parse_json_protocol(options, &filename, &local_err);
if (local_err) {
- ret = -EINVAL;
goto fail;
}
drv = bdrv_find_format(drvname);
if (!drv) {
error_setg(errp, "Unknown driver: '%s'", drvname);
- ret = -EINVAL;
goto fail;
}
}
file = bdrv_open_child(filename, options, "file", bs,
&child_file, true, &local_err);
if (local_err) {
- ret = -EINVAL;
goto fail;
}
}
qdict_put(options, "driver", qstring_from_str(drv->format_name));
} else if (!drv) {
error_setg(errp, "Must specify either driver or file");
- ret = -EINVAL;
goto fail;
}
drv->format_name, entry->key);
}
- ret = -EINVAL;
goto close_and_fail;
}
if (!bdrv_key_required(bs)) {
- if (bs->blk) {
- blk_dev_change_media_cb(bs->blk, true);
- }
+ bdrv_parent_cb_change_media(bs, true);
} else if (!runstate_check(RUN_STATE_PRELAUNCH)
&& !runstate_check(RUN_STATE_INMIGRATE)
&& !runstate_check(RUN_STATE_PAUSED)) { /* HACK */
error_setg(errp,
"Guest must be stopped for opening of encrypted image");
- ret = -EBUSY;
goto close_and_fail;
}
QDECREF(options);
- *pbs = bs;
/* For snapshot=on, create a temporary qcow2 overlay. bs points to the
* temporary snapshot afterwards. */
if (snapshot_flags) {
- ret = bdrv_append_temp_snapshot(bs, snapshot_flags, snapshot_options,
- &local_err);
+ BlockDriverState *snapshot_bs;
+ snapshot_bs = bdrv_append_temp_snapshot(bs, snapshot_flags,
+ snapshot_options, &local_err);
snapshot_options = NULL;
if (local_err) {
goto close_and_fail;
}
+ /* We are not going to return bs but the overlay on top of it
+ * (snapshot_bs); thus, we have to drop the strong reference to bs
+ * (which we obtained by calling bdrv_new()). bs will not be deleted,
+ * though, because the overlay still has a reference to it. */
+ bdrv_unref(bs);
+ bs = snapshot_bs;
}
- return 0;
+ return bs;
fail:
if (file != NULL) {
QDECREF(bs->options);
QDECREF(options);
bs->options = NULL;
- if (!*pbs) {
- /* If *pbs is NULL, a new BDS has been created in this function and
- needs to be freed now. Otherwise, it does not need to be closed,
- since it has not really been opened yet. */
- bdrv_unref(bs);
- }
+ bdrv_unref(bs);
if (local_err) {
error_propagate(errp, local_err);
}
- return ret;
+ return NULL;
close_and_fail:
- /* See fail path, but now the BDS has to be always closed */
- if (*pbs) {
- bdrv_close(bs);
- } else {
- bdrv_unref(bs);
- }
+ bdrv_unref(bs);
QDECREF(snapshot_options);
QDECREF(options);
if (local_err) {
error_propagate(errp, local_err);
}
- return ret;
+ return NULL;
}
-int bdrv_open(BlockDriverState **pbs, const char *filename,
- const char *reference, QDict *options, int flags, Error **errp)
+BlockDriverState *bdrv_open(const char *filename, const char *reference,
+ QDict *options, int flags, Error **errp)
{
- return bdrv_open_inherit(pbs, filename, reference, options, flags, NULL,
+ return bdrv_open_inherit(filename, reference, options, flags, NULL,
NULL, errp);
}
BdrvAioNotifier *ban, *ban_next;
assert(!bs->job);
+ assert(!bs->refcnt);
bdrv_drained_begin(bs); /* complete I/O */
bdrv_flush(bs);
bdrv_release_named_dirty_bitmaps(bs);
assert(QLIST_EMPTY(&bs->dirty_bitmaps));
- if (bs->blk) {
- blk_dev_change_media_cb(bs->blk, false);
- }
-
if (bs->drv) {
BdrvChild *child, *next;
bs->encrypted = 0;
bs->valid_key = 0;
bs->sg = 0;
- bs->zero_beyond_eof = false;
QDECREF(bs->options);
QDECREF(bs->explicit_options);
bs->options = NULL;
void bdrv_close_all(void)
{
- BlockDriverState *bs;
- AioContext *aio_context;
+ block_job_cancel_sync_all();
/* Drop references from requests still in flight, such as canceled block
* jobs whose AIO context has not been polled yet */
blk_remove_all_bs();
blockdev_close_all_bdrv_states();
- /* Cancel all block jobs */
- while (!QTAILQ_EMPTY(&all_bdrv_states)) {
- QTAILQ_FOREACH(bs, &all_bdrv_states, bs_list) {
- aio_context = bdrv_get_aio_context(bs);
-
- aio_context_acquire(aio_context);
- if (bs->job) {
- block_job_cancel_sync(bs->job);
- aio_context_release(aio_context);
- break;
- }
- aio_context_release(aio_context);
- }
-
- /* All the remaining BlockDriverStates are referenced directly or
- * indirectly from block jobs, so there needs to be at least one BDS
- * directly used by a block job */
- assert(bs);
- }
-}
-
-/* Fields that need to stay with the top-level BDS */
-static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
- BlockDriverState *bs_src)
-{
- /* move some fields that need to stay attached to the device */
+ assert(QTAILQ_EMPTY(&all_bdrv_states));
}
static void change_parent_backing_link(BlockDriverState *from,
BlockDriverState *to)
{
- BdrvChild *c, *next;
-
- if (from->blk) {
- /* FIXME We bypass blk_set_bs(), so we need to make these updates
- * manually. The root problem is not in this change function, but the
- * existence of BlockDriverState.blk. */
- to->blk = from->blk;
- from->blk = NULL;
- }
+ BdrvChild *c, *next, *to_c;
QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
+ if (c->role == &child_backing) {
+ /* @from is generally not allowed to be a backing file, except for
+ * when @to is the overlay. In that case, @from may not be replaced
+ * by @to as @to's backing node. */
+ QLIST_FOREACH(to_c, &to->children, next) {
+ if (to_c == c) {
+ break;
+ }
+ }
+ if (to_c) {
+ continue;
+ }
+ }
+
assert(c->role != &child_backing);
- c->bs = to;
- QLIST_REMOVE(c, next_parent);
- QLIST_INSERT_HEAD(&to->parents, c, next_parent);
bdrv_ref(to);
+ bdrv_replace_child(c, to);
bdrv_unref(from);
}
}
-static void swap_feature_fields(BlockDriverState *bs_top,
- BlockDriverState *bs_new)
-{
- BlockDriverState tmp;
-
- bdrv_move_feature_fields(&tmp, bs_top);
- bdrv_move_feature_fields(bs_top, bs_new);
- bdrv_move_feature_fields(bs_new, &tmp);
-}
-
/*
* Add new bs contents at the top of an image chain while the chain is
* live, while keeping required fields on the top layer.
bdrv_ref(bs_top);
- /* Some fields always stay on top of the backing file chain */
- swap_feature_fields(bs_top, bs_new);
-
change_parent_backing_link(bs_top, bs_new);
bdrv_set_backing_hd(bs_new, bs_top);
bdrv_unref(bs_top);
bdrv_ref(old);
- if (old->blk) {
- /* As long as these fields aren't in BlockBackend, but in the top-level
- * BlockDriverState, it's not possible for a BDS to have two BBs.
- *
- * We really want to copy the fields from old to new, but we go for a
- * swap instead so that pointers aren't duplicated and cause trouble.
- * (Also, bdrv_swap() used to do the same.) */
- assert(!new->blk);
- swap_feature_fields(old, new);
- }
change_parent_backing_link(old, new);
- /* Change backing files if a previously independent node is added to the
- * chain. For active commit, we replace top by its own (indirect) backing
- * file and don't do anything here so we don't build a loop. */
- if (new->backing == NULL && !bdrv_chain_contains(backing_bs(old), new)) {
- bdrv_set_backing_hd(new, backing_bs(old));
- bdrv_set_backing_hd(old, NULL);
- }
-
bdrv_unref(old);
}
if (ret == 0) {
ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
bdrv_dirty_bitmap_truncate(bs);
- if (bs->blk) {
- blk_dev_resize_cb(bs->blk);
- }
+ bdrv_parent_cb_resize(bs);
}
return ret;
}
if (ret < 0) {
bs->valid_key = 0;
} else if (!bs->valid_key) {
+ /* call the change callback now, we skipped it on open */
bs->valid_key = 1;
- if (bs->blk) {
- /* call the change callback now, we skipped it on open */
- blk_dev_change_media_cb(bs->blk, true);
- }
+ bdrv_parent_cb_change_media(bs, true);
}
return ret;
}
return QTAILQ_NEXT(bs, node_list);
}
-/* Iterates over all top-level BlockDriverStates, i.e. BDSs that are owned by
- * the monitor or attached to a BlockBackend */
-BlockDriverState *bdrv_next(BlockDriverState *bs)
+const char *bdrv_get_node_name(const BlockDriverState *bs)
{
- if (!bs || bs->blk) {
- bs = blk_next_root_bs(bs);
- if (bs) {
- return bs;
- }
- }
-
- /* Ignore all BDSs that are attached to a BlockBackend here; they have been
- * handled by the above block already */
- do {
- bs = bdrv_next_monitor_owned(bs);
- } while (bs && bs->blk);
- return bs;
+ return bs->node_name;
}
-const char *bdrv_get_node_name(const BlockDriverState *bs)
+const char *bdrv_get_parent_name(const BlockDriverState *bs)
{
- return bs->node_name;
+ BdrvChild *c;
+ const char *name;
+
+ /* If multiple parents have a name, just pick the first one. */
+ QLIST_FOREACH(c, &bs->parents, next_parent) {
+ if (c->role->get_name) {
+ name = c->role->get_name(c);
+ if (name && *name) {
+ return name;
+ }
+ }
+ }
+
+ return NULL;
}
/* TODO check what callers really want: bs->node_name or blk_name() */
const char *bdrv_get_device_name(const BlockDriverState *bs)
{
- return bs->blk ? blk_name(bs->blk) : "";
+ return bdrv_get_parent_name(bs) ?: "";
}
/* This can be used to identify nodes that might not have a device
* absent, then this returns an empty (non-null) string. */
const char *bdrv_get_device_or_node_name(const BlockDriverState *bs)
{
- return bs->blk ? blk_name(bs->blk) : bs->node_name;
+ return bdrv_get_parent_name(bs) ?: bs->node_name;
}
int bdrv_get_flags(BlockDriverState *bs)
void bdrv_invalidate_cache_all(Error **errp)
{
- BlockDriverState *bs = NULL;
+ BlockDriverState *bs;
Error *local_err = NULL;
+ BdrvNextIterator it;
- while ((bs = bdrv_next(bs)) != NULL) {
+ for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
int bdrv_inactivate_all(void)
{
BlockDriverState *bs = NULL;
+ BdrvNextIterator it;
int ret = 0;
int pass;
- while ((bs = bdrv_next(bs)) != NULL) {
+ for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
aio_context_acquire(bdrv_get_aio_context(bs));
}
* the second pass sets the BDRV_O_INACTIVE flag so that no further write
* is allowed. */
for (pass = 0; pass < 2; pass++) {
- bs = NULL;
- while ((bs = bdrv_next(bs)) != NULL) {
+ for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
ret = bdrv_inactivate_recurse(bs, pass);
if (ret < 0) {
goto out;
}
out:
- bs = NULL;
- while ((bs = bdrv_next(bs)) != NULL) {
+ for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
aio_context_release(bdrv_get_aio_context(bs));
}
qstring_from_str(backing_fmt));
}
- bs = NULL;
- ret = bdrv_open(&bs, full_backing, NULL, backing_options,
- back_flags, &local_err);
+ bs = bdrv_open(full_backing, NULL, backing_options, back_flags,
+ &local_err);
g_free(full_backing);
- if (ret < 0) {
+ if (!bs) {
goto out;
}
size = bdrv_getlength(bs);
void bdrv_detach_aio_context(BlockDriverState *bs)
{
BdrvAioNotifier *baf;
+ BdrvChild *child;
if (!bs->drv) {
return;
if (bs->drv->bdrv_detach_aio_context) {
bs->drv->bdrv_detach_aio_context(bs);
}
- if (bs->file) {
- bdrv_detach_aio_context(bs->file->bs);
- }
- if (bs->backing) {
- bdrv_detach_aio_context(bs->backing->bs);
+ QLIST_FOREACH(child, &bs->children, next) {
+ bdrv_detach_aio_context(child->bs);
}
bs->aio_context = NULL;
AioContext *new_context)
{
BdrvAioNotifier *ban;
+ BdrvChild *child;
if (!bs->drv) {
return;
bs->aio_context = new_context;
- if (bs->backing) {
- bdrv_attach_aio_context(bs->backing->bs, new_context);
- }
- if (bs->file) {
- bdrv_attach_aio_context(bs->file->bs, new_context);
+ QLIST_FOREACH(child, &bs->children, next) {
+ bdrv_attach_aio_context(child->bs, new_context);
}
if (bs->drv->bdrv_attach_aio_context) {
bs->drv->bdrv_attach_aio_context(bs, new_context);
*/
bool bdrv_is_first_non_filter(BlockDriverState *candidate)
{
- BlockDriverState *bs = NULL;
+ BlockDriverState *bs;
+ BdrvNextIterator it;
/* walk down the bs forest recursively */
- while ((bs = bdrv_next(bs)) != NULL) {
+ for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
bool perm;
/* try to recurse in this top level bs */
projects / mirror_qemu.git / blobdiff