#include "qemu/timer.h"
#include "qemu/cutils.h"
#include "qemu/id.h"
+#include "qemu/range.h"
+#include "qemu/rcu.h"
#include "block/coroutines.h"
#ifdef CONFIG_BSD
BdrvChildRole child_role,
Error **errp);
+static bool bdrv_recurse_has_child(BlockDriverState *bs,
+ BlockDriverState *child);
+
static void bdrv_replace_child_noperm(BdrvChild *child,
BlockDriverState *new_bs);
static void bdrv_remove_file_or_backing_child(BlockDriverState *bs,
qemu_co_queue_init(&bs->flush_queue);
+ qemu_co_mutex_init(&bs->bsc_modify_lock);
+ bs->block_status_cache = g_new0(BdrvBlockStatusCache, 1);
+
for (i = 0; i < bdrv_drain_all_count; i++) {
bdrv_drained_begin(bs);
}
return ret;
}
-BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
- int flags, Error **errp)
+/*
+ * Create and open a block node.
+ *
+ * @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 qobject_ref() before calling bdrv_open.
+ */
+BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv,
+ const char *node_name,
+ QDict *options, int flags,
+ Error **errp)
{
BlockDriverState *bs;
int ret;
bs = bdrv_new();
bs->open_flags = flags;
- bs->explicit_options = qdict_new();
- bs->options = qdict_new();
+ bs->options = options ?: qdict_new();
+ bs->explicit_options = qdict_clone_shallow(bs->options);
bs->opaque = NULL;
update_options_from_flags(bs->options, flags);
return bs;
}
+/* Create and open a block node. */
+BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
+ int flags, Error **errp)
+{
+ return bdrv_new_open_driver_opts(drv, node_name, NULL, flags, errp);
+}
+
QemuOptsList bdrv_runtime_opts = {
.name = "bdrv_common",
.head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head),
int drain_saldo;
assert(!child->frozen);
+ assert(old_bs != new_bs);
if (old_bs && new_bs) {
assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
assert(parent_bs->drv);
+ if (bdrv_recurse_has_child(child_bs, parent_bs)) {
+ error_setg(errp, "Making '%s' a %s child of '%s' would create a cycle",
+ child_bs->node_name, child_name, parent_bs->node_name);
+ return -EINVAL;
+ }
+
bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm);
bdrv_child_perm(parent_bs, child_bs, NULL, child_role, NULL,
perm, shared_perm, &perm, &shared_perm);
bs->explicit_options = NULL;
qobject_unref(bs->full_open_options);
bs->full_open_options = NULL;
+ g_free(bs->block_status_cache);
+ bs->block_status_cache = NULL;
bdrv_release_named_dirty_bitmaps(bs);
assert(QLIST_EMPTY(&bs->dirty_bitmaps));
return ret;
}
+/* Not for empty child */
+int bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs,
+ Error **errp)
+{
+ int ret;
+ Transaction *tran = tran_new();
+ g_autoptr(GHashTable) found = NULL;
+ g_autoptr(GSList) refresh_list = NULL;
+ BlockDriverState *old_bs = child->bs;
+
+ bdrv_ref(old_bs);
+ bdrv_drained_begin(old_bs);
+ bdrv_drained_begin(new_bs);
+
+ bdrv_replace_child_tran(child, new_bs, tran);
+
+ found = g_hash_table_new(NULL, NULL);
+ refresh_list = bdrv_topological_dfs(refresh_list, found, old_bs);
+ refresh_list = bdrv_topological_dfs(refresh_list, found, new_bs);
+
+ ret = bdrv_list_refresh_perms(refresh_list, NULL, tran, errp);
+
+ tran_finalize(tran, ret);
+
+ bdrv_drained_end(old_bs);
+ bdrv_drained_end(new_bs);
+ bdrv_unref(old_bs);
+
+ return ret;
+}
+
static void bdrv_delete(BlockDriverState *bs)
{
assert(bdrv_op_blocker_is_empty(bs));
g_free(bs);
}
-BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options,
+
+/*
+ * Replace @bs by newly created block node.
+ *
+ * @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 qobject_ref() before calling bdrv_open.
+ */
+BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *options,
int flags, Error **errp)
{
- BlockDriverState *new_node_bs;
- Error *local_err = NULL;
+ ERRP_GUARD();
+ int ret;
+ BlockDriverState *new_node_bs = NULL;
+ const char *drvname, *node_name;
+ BlockDriver *drv;
+
+ drvname = qdict_get_try_str(options, "driver");
+ if (!drvname) {
+ error_setg(errp, "driver is not specified");
+ goto fail;
+ }
+
+ drv = bdrv_find_format(drvname);
+ if (!drv) {
+ error_setg(errp, "Unknown driver: '%s'", drvname);
+ goto fail;
+ }
+
+ node_name = qdict_get_try_str(options, "node-name");
- new_node_bs = bdrv_open(NULL, NULL, node_options, flags, errp);
- if (new_node_bs == NULL) {
+ new_node_bs = bdrv_new_open_driver_opts(drv, node_name, options, flags,
+ errp);
+ options = NULL; /* bdrv_new_open_driver() eats options */
+ if (!new_node_bs) {
error_prepend(errp, "Could not create node: ");
- return NULL;
+ goto fail;
}
bdrv_drained_begin(bs);
- bdrv_replace_node(bs, new_node_bs, &local_err);
+ ret = bdrv_replace_node(bs, new_node_bs, errp);
bdrv_drained_end(bs);
- if (local_err) {
- bdrv_unref(new_node_bs);
- error_propagate(errp, local_err);
- return NULL;
+ if (ret < 0) {
+ error_prepend(errp, "Could not replace node: ");
+ goto fail;
}
return new_node_bs;
+
+fail:
+ qobject_unref(options);
+ bdrv_unref(new_node_bs);
+ return NULL;
}
/*
void bdrv_init(void)
{
+#ifdef CONFIG_BDRV_WHITELIST_TOOLS
+ use_bdrv_whitelist = 1;
+#endif
module_call_init(MODULE_INIT_BLOCK);
}
{
BdrvChild *child, *parent;
int ret;
+ uint64_t cumulative_perms, cumulative_shared_perms;
if (!bs->drv) {
return -ENOMEDIUM;
}
}
+ bdrv_get_cumulative_perm(bs, &cumulative_perms,
+ &cumulative_shared_perms);
+ if (cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) {
+ /* Our inactive parents still need write access. Inactivation failed. */
+ return -EPERM;
+ }
+
bs->open_flags |= BDRV_O_INACTIVE;
/*
{
return bdrv_skip_filters(bdrv_cow_bs(bdrv_skip_filters(bs)));
}
+
+/**
+ * Check whether [offset, offset + bytes) overlaps with the cached
+ * block-status data region.
+ *
+ * If so, and @pnum is not NULL, set *pnum to `bsc.data_end - offset`,
+ * which is what bdrv_bsc_is_data()'s interface needs.
+ * Otherwise, *pnum is not touched.
+ */
+static bool bdrv_bsc_range_overlaps_locked(BlockDriverState *bs,
+ int64_t offset, int64_t bytes,
+ int64_t *pnum)
+{
+ BdrvBlockStatusCache *bsc = qatomic_rcu_read(&bs->block_status_cache);
+ bool overlaps;
+
+ overlaps =
+ qatomic_read(&bsc->valid) &&
+ ranges_overlap(offset, bytes, bsc->data_start,
+ bsc->data_end - bsc->data_start);
+
+ if (overlaps && pnum) {
+ *pnum = bsc->data_end - offset;
+ }
+
+ return overlaps;
+}
+
+/**
+ * See block_int.h for this function's documentation.
+ */
+bool bdrv_bsc_is_data(BlockDriverState *bs, int64_t offset, int64_t *pnum)
+{
+ RCU_READ_LOCK_GUARD();
+
+ return bdrv_bsc_range_overlaps_locked(bs, offset, 1, pnum);
+}
+
+/**
+ * See block_int.h for this function's documentation.
+ */
+void bdrv_bsc_invalidate_range(BlockDriverState *bs,
+ int64_t offset, int64_t bytes)
+{
+ RCU_READ_LOCK_GUARD();
+
+ if (bdrv_bsc_range_overlaps_locked(bs, offset, bytes, NULL)) {
+ qatomic_set(&bs->block_status_cache->valid, false);
+ }
+}
+
+/**
+ * See block_int.h for this function's documentation.
+ */
+void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes)
+{
+ BdrvBlockStatusCache *new_bsc = g_new(BdrvBlockStatusCache, 1);
+ BdrvBlockStatusCache *old_bsc;
+
+ *new_bsc = (BdrvBlockStatusCache) {
+ .valid = true,
+ .data_start = offset,
+ .data_end = offset + bytes,
+ };
+
+ QEMU_LOCK_GUARD(&bs->bsc_modify_lock);
+
+ old_bsc = qatomic_rcu_read(&bs->block_status_cache);
+ qatomic_rcu_set(&bs->block_status_cache, new_bsc);
+ if (old_bsc) {
+ g_free_rcu(old_bsc, rcu);
+ }
+}