int quiesce_counter;
VMChangeStateEntry *vmsh;
+ bool force_allow_inactivate;
};
typedef struct BlockBackendAIOCB {
}
}
+void blk_set_force_allow_inactivate(BlockBackend *blk)
+{
+ blk->force_allow_inactivate = true;
+}
+
+static bool blk_can_inactivate(BlockBackend *blk)
+{
+ /* If it is a guest device, inactivate is ok. */
+ if (blk->dev || blk_name(blk)[0]) {
+ return true;
+ }
+
+ /* Inactivating means no more writes to the image can be done,
+ * even if those writes would be changes invisible to the
+ * guest. For block job BBs that satisfy this, we can just allow
+ * it. This is the case for mirror job source, which is required
+ * by libvirt non-shared block migration. */
+ if (!(blk->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED))) {
+ return true;
+ }
+
+ return blk->force_allow_inactivate;
+}
+
static int blk_root_inactivate(BdrvChild *child)
{
BlockBackend *blk = child->opaque;
return 0;
}
- /* Only inactivate BlockBackends for guest devices (which are inactive at
- * this point because the VM is stopped) and unattached monitor-owned
- * BlockBackends. If there is still any other user like a block job, then
- * we simply can't inactivate the image. */
- if (!blk->dev && !blk_name(blk)[0]) {
+ if (!blk_can_inactivate(blk)) {
return -EPERM;
}
blk->shared_perm = shared_perm;
blk_set_enable_write_cache(blk, true);
- qemu_co_mutex_init(&blk->public.throttled_reqs_lock);
- qemu_co_queue_init(&blk->public.throttled_reqs[0]);
- qemu_co_queue_init(&blk->public.throttled_reqs[1]);
block_acct_init(&blk->stats);
notifier_list_init(&blk->remove_bs_notifiers);
{
BlockBackend *blk;
BlockDriverState *bs;
- uint64_t perm;
+ uint64_t perm = 0;
/* blk_new_open() is mainly used in .bdrv_create implementations and the
* tools where sharing isn't a concern because the BDS stays private, so we
* caller of blk_new_open() doesn't make use of the permissions, but they
* shouldn't hurt either. We can still share everything here because the
* guest devices will add their own blockers if they can't share. */
- perm = BLK_PERM_CONSISTENT_READ;
- if (flags & BDRV_O_RDWR) {
- perm |= BLK_PERM_WRITE;
+ if ((flags & BDRV_O_NO_IO) == 0) {
+ perm |= BLK_PERM_CONSISTENT_READ;
+ if (flags & BDRV_O_RDWR) {
+ perm |= BLK_PERM_WRITE;
+ }
}
if (flags & BDRV_O_RESIZE) {
perm |= BLK_PERM_RESIZE;
assert(!blk->refcnt);
assert(!blk->name);
assert(!blk->dev);
- if (blk->public.throttle_state) {
+ if (blk->public.throttle_group_member.throttle_state) {
blk_io_limits_disable(blk);
}
if (blk->root) {
* the monitor or attached to a BlockBackend */
BlockDriverState *bdrv_next(BdrvNextIterator *it)
{
- BlockDriverState *bs;
+ BlockDriverState *bs, *old_bs;
+
+ /* Must be called from the main loop */
+ assert(qemu_get_current_aio_context() == qemu_get_aio_context());
/* First, return all root nodes of BlockBackends. In order to avoid
* returning a BDS twice when multiple BBs refer to it, we only return it
* if the BB is the first one in the parent list of the BDS. */
if (it->phase == BDRV_NEXT_BACKEND_ROOTS) {
+ BlockBackend *old_blk = it->blk;
+
+ old_bs = old_blk ? blk_bs(old_blk) : NULL;
+
do {
it->blk = blk_all_next(it->blk);
bs = it->blk ? blk_bs(it->blk) : NULL;
} while (it->blk && (bs == NULL || bdrv_first_blk(bs) != it->blk));
+ if (it->blk) {
+ blk_ref(it->blk);
+ }
+ blk_unref(old_blk);
+
if (bs) {
+ bdrv_ref(bs);
+ bdrv_unref(old_bs);
return bs;
}
it->phase = BDRV_NEXT_MONITOR_OWNED;
+ } else {
+ old_bs = it->bs;
}
/* Then return the monitor-owned BDSes without a BB attached. Ignore all
bs = it->bs;
} while (bs && bdrv_has_blk(bs));
+ if (bs) {
+ bdrv_ref(bs);
+ }
+ bdrv_unref(old_bs);
+
return bs;
}
-BlockDriverState *bdrv_first(BdrvNextIterator *it)
+static void bdrv_next_reset(BdrvNextIterator *it)
{
*it = (BdrvNextIterator) {
.phase = BDRV_NEXT_BACKEND_ROOTS,
};
+}
+BlockDriverState *bdrv_first(BdrvNextIterator *it)
+{
+ bdrv_next_reset(it);
return bdrv_next(it);
}
+/* Must be called when aborting a bdrv_next() iteration before
+ * bdrv_next() returns NULL */
+void bdrv_next_cleanup(BdrvNextIterator *it)
+{
+ /* Must be called from the main loop */
+ assert(qemu_get_current_aio_context() == qemu_get_aio_context());
+
+ if (it->phase == BDRV_NEXT_BACKEND_ROOTS) {
+ if (it->blk) {
+ bdrv_unref(blk_bs(it->blk));
+ blk_unref(it->blk);
+ }
+ } else {
+ bdrv_unref(it->bs);
+ }
+
+ bdrv_next_reset(it);
+}
+
/*
* Add a BlockBackend into the list of backends referenced by the monitor, with
* the given @name acting as the handle for the monitor.
*/
void blk_remove_bs(BlockBackend *blk)
{
+ ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
+ BlockDriverState *bs;
+
notifier_list_notify(&blk->remove_bs_notifiers, blk);
- if (blk->public.throttle_state) {
- throttle_timers_detach_aio_context(&blk->public.throttle_timers);
+ if (tgm->throttle_state) {
+ bs = blk_bs(blk);
+ bdrv_drained_begin(bs);
+ throttle_group_detach_aio_context(tgm);
+ throttle_group_attach_aio_context(tgm, qemu_get_aio_context());
+ bdrv_drained_end(bs);
}
blk_update_root_state(blk);
*/
int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
{
+ ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
blk->root = bdrv_root_attach_child(bs, "root", &child_root,
blk->perm, blk->shared_perm, blk, errp);
if (blk->root == NULL) {
bdrv_ref(bs);
notifier_list_notify(&blk->insert_bs_notifiers, blk);
- if (blk->public.throttle_state) {
- throttle_timers_attach_aio_context(
- &blk->public.throttle_timers, bdrv_get_aio_context(bs));
+ if (tgm->throttle_state) {
+ throttle_group_detach_aio_context(tgm);
+ throttle_group_attach_aio_context(tgm, bdrv_get_aio_context(bs));
}
return 0;
bdrv_inc_in_flight(bs);
/* throttling disk I/O */
- if (blk->public.throttle_state) {
- throttle_group_co_io_limits_intercept(blk, bytes, false);
+ if (blk->public.throttle_group_member.throttle_state) {
+ throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
+ bytes, false);
}
ret = bdrv_co_preadv(blk->root, offset, bytes, qiov, flags);
}
bdrv_inc_in_flight(bs);
-
/* throttling disk I/O */
- if (blk->public.throttle_state) {
- throttle_group_co_io_limits_intercept(blk, bytes, true);
+ if (blk->public.throttle_group_member.throttle_state) {
+ throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
+ bytes, true);
}
if (!blk->enable_write_cache) {
void blk_set_aio_context(BlockBackend *blk, AioContext *new_context)
{
BlockDriverState *bs = blk_bs(blk);
+ ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
if (bs) {
- if (blk->public.throttle_state) {
- throttle_timers_detach_aio_context(&blk->public.throttle_timers);
+ if (tgm->throttle_state) {
+ bdrv_drained_begin(bs);
+ throttle_group_detach_aio_context(tgm);
+ throttle_group_attach_aio_context(tgm, new_context);
+ bdrv_drained_end(bs);
}
bdrv_set_aio_context(bs, new_context);
- if (blk->public.throttle_state) {
- throttle_timers_attach_aio_context(&blk->public.throttle_timers,
- new_context);
- }
}
}
/* throttling disk I/O limits */
void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg)
{
- throttle_group_config(blk, cfg);
+ throttle_group_config(&blk->public.throttle_group_member, cfg);
}
void blk_io_limits_disable(BlockBackend *blk)
{
- assert(blk->public.throttle_state);
- bdrv_drained_begin(blk_bs(blk));
- throttle_group_unregister_blk(blk);
- bdrv_drained_end(blk_bs(blk));
+ BlockDriverState *bs = blk_bs(blk);
+ ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
+ assert(tgm->throttle_state);
+ if (bs) {
+ bdrv_drained_begin(bs);
+ }
+ throttle_group_unregister_tgm(tgm);
+ if (bs) {
+ bdrv_drained_end(bs);
+ }
}
/* should be called before blk_set_io_limits if a limit is set */
void blk_io_limits_enable(BlockBackend *blk, const char *group)
{
- assert(!blk->public.throttle_state);
- throttle_group_register_blk(blk, group);
+ assert(!blk->public.throttle_group_member.throttle_state);
+ throttle_group_register_tgm(&blk->public.throttle_group_member,
+ group, blk_get_aio_context(blk));
}
void blk_io_limits_update_group(BlockBackend *blk, const char *group)
{
/* this BB is not part of any group */
- if (!blk->public.throttle_state) {
+ if (!blk->public.throttle_group_member.throttle_state) {
return;
}
/* this BB is a part of the same group than the one we want */
- if (!g_strcmp0(throttle_group_get_name(blk), group)) {
+ if (!g_strcmp0(throttle_group_get_name(&blk->public.throttle_group_member),
+ group)) {
return;
}
/* Note that blk->root may not be accessible here yet if we are just
* attaching to a BlockDriverState that is drained. Use child instead. */
- if (atomic_fetch_inc(&blk->public.io_limits_disabled) == 0) {
- throttle_group_restart_blk(blk);
+ if (atomic_fetch_inc(&blk->public.throttle_group_member.io_limits_disabled) == 0) {
+ throttle_group_restart_tgm(&blk->public.throttle_group_member);
}
}
BlockBackend *blk = child->opaque;
assert(blk->quiesce_counter);
- assert(blk->public.io_limits_disabled);
- atomic_dec(&blk->public.io_limits_disabled);
+ assert(blk->public.throttle_group_member.io_limits_disabled);
+ atomic_dec(&blk->public.throttle_group_member.io_limits_disabled);
if (--blk->quiesce_counter == 0) {
if (blk->dev_ops && blk->dev_ops->drained_end) {
projects / qemu.git / blobdiff