static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, int64_t granularity,
int64_t buf_size,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base)
{
MirrorBlockJob *s;
if (granularity == 0) {
/* Choose the default granularity based on the target file's cluster
* size, clamped between 4k and 64k. */
BlockDriverInfo bdi;
if (bdrv_get_info(target, &bdi) >= 0 && bdi.cluster_size != 0) {
granularity = MAX(4096, bdi.cluster_size);
granularity = MIN(65536, granularity);
} else {
granularity = 65536;
}
}
assert ((granularity & (granularity - 1)) == 0);
if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
return;
}
s = block_job_create(driver, bs, speed, cb, opaque, errp);
if (!s) {
return;
}
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
s->on_target_error = on_target_error;
s->target = target;
s->is_none_mode = is_none_mode;
s->base = base;
s->granularity = granularity;
s->buf_size = MAX(buf_size, granularity);
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, errp);
if (!s->dirty_bitmap) {
return;
}
bdrv_set_enable_write_cache(s->target, true);
bdrv_set_on_error(s->target, on_target_error, on_target_error);
bdrv_iostatus_enable(s->target);
s->common.co = qemu_coroutine_create(mirror_run);
trace_mirror_start(bs, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
}
/* Create a block job that completes with a given return code after a given
* number of event loop iterations. The return code is stored in the given
* result pointer.
*
* The event loop iterations can either be handled automatically with a 0 delay
* timer, or they can be stepped manually by entering the coroutine.
*/
static BlockJob *test_block_job_start(unsigned int iterations,
bool use_timer,
int rc, int *result, BlockJobTxn *txn)
{
BlockDriverState *bs;
TestBlockJob *s;
TestBlockJobCBData *data;
static unsigned counter;
char job_id[24];
data = g_new0(TestBlockJobCBData, 1);
bs = bdrv_open("null-co://", NULL, NULL, 0, &error_abort);
g_assert_nonnull(bs);
snprintf(job_id, sizeof(job_id), "job%u", counter++);
s = block_job_create(job_id, &test_block_job_driver, txn, bs,
0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT,
test_block_job_cb, data, &error_abort);
s->iterations = iterations;
s->use_timer = use_timer;
s->rc = rc;
s->result = result;
data->job = s;
data->result = result;
return &s->common;
}
/* Create a block job that completes with a given return code after a given
* number of event loop iterations. The return code is stored in the given
* result pointer.
*
* The event loop iterations can either be handled automatically with a 0 delay
* timer, or they can be stepped manually by entering the coroutine.
*/
static BlockJob *test_block_job_start(unsigned int iterations,
bool use_timer,
int rc, int *result)
{
BlockDriverState *bs;
TestBlockJob *s;
TestBlockJobCBData *data;
static unsigned counter;
char job_id[24];
data = g_new0(TestBlockJobCBData, 1);
bs = bdrv_new();
snprintf(job_id, sizeof(job_id), "job%u", counter++);
s = block_job_create(job_id, &test_block_job_driver, bs, 0,
BLOCK_JOB_DEFAULT, test_block_job_cb,
data, &error_abort);
s->iterations = iterations;
s->use_timer = use_timer;
s->rc = rc;
s->result = result;
s->common.co = qemu_coroutine_create(test_block_job_run, s);
data->job = s;
data->result = result;
qemu_coroutine_enter(s->common.co);
return &s->common;
}
static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, uint32_t granularity,
int64_t buf_size,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
BlockCompletionFunc *cb,
void *opaque, Error **errp,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base)
{
MirrorBlockJob *s;
if (granularity == 0) {
granularity = bdrv_get_default_bitmap_granularity(target);
}
assert ((granularity & (granularity - 1)) == 0);
if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
return;
}
s = block_job_create(driver, bs, speed, cb, opaque, errp);
if (!s) {
return;
}
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
s->on_target_error = on_target_error;
s->target = target;
s->is_none_mode = is_none_mode;
s->base = base;
s->granularity = granularity;
s->buf_size = MAX(buf_size, granularity);
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
if (!s->dirty_bitmap) {
return;
}
bdrv_set_enable_write_cache(s->target, true);
bdrv_set_on_error(s->target, on_target_error, on_target_error);
bdrv_iostatus_enable(s->target);
s->common.co = qemu_coroutine_create(mirror_run);
trace_mirror_start(bs, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
}
static BlockJob *do_test_id(BlockBackend *blk, const char *id,
bool should_succeed)
{
BlockJob *job;
Error *errp = NULL;
job = block_job_create(id, &test_block_job_driver, blk_bs(blk),
0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT, block_job_cb,
NULL, &errp);
if (should_succeed) {
g_assert_null(errp);
g_assert_nonnull(job);
if (id) {
g_assert_cmpstr(job->id, ==, id);
} else {
g_assert_cmpstr(job->id, ==, blk_name(blk));
}
} else {
/* Create a block job that completes with a given return code after a given
* number of event loop iterations. The return code is stored in the given
* result pointer.
*
* The event loop iterations can either be handled automatically with a 0 delay
* timer, or they can be stepped manually by entering the coroutine.
*/
static BlockJob *test_block_job_start(unsigned int iterations,
bool use_timer,
int rc, int *result)
{
BlockDriverState *bs;
TestBlockJob *s;
TestBlockJobCBData *data;
data = g_new0(TestBlockJobCBData, 1);
bs = bdrv_new();
s = block_job_create(&test_block_job_driver, bs, 0, test_block_job_cb,
data, &error_abort);
s->iterations = iterations;
s->use_timer = use_timer;
s->rc = rc;
s->result = result;
s->common.co = qemu_coroutine_create(test_block_job_run);
data->job = s;
data->result = result;
qemu_coroutine_enter(s->common.co, s);
return &s->common;
}
static void mirror_start_job(const char *job_id, BlockDriverState *bs,
int creation_flags, BlockDriverState *target,
const char *replaces, int64_t speed,
uint32_t granularity, int64_t buf_size,
BlockMirrorBackingMode backing_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
bool unmap,
BlockCompletionFunc *cb,
void *opaque,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base,
bool auto_complete, const char *filter_node_name,
bool is_mirror,
Error **errp)
{
MirrorBlockJob *s;
BlockDriverState *mirror_top_bs;
bool target_graph_mod;
bool target_is_backing;
Error *local_err = NULL;
int ret;
if (granularity == 0) {
granularity = bdrv_get_default_bitmap_granularity(target);
}
assert(is_power_of_2(granularity));
if (buf_size < 0) {
error_setg(errp, "Invalid parameter 'buf-size'");
return;
}
if (buf_size == 0) {
buf_size = DEFAULT_MIRROR_BUF_SIZE;
}
/* In the case of active commit, add dummy driver to provide consistent
* reads on the top, while disabling it in the intermediate nodes, and make
* the backing chain writable. */
mirror_top_bs = bdrv_new_open_driver(&bdrv_mirror_top, filter_node_name,
BDRV_O_RDWR, errp);
if (mirror_top_bs == NULL) {
return;
}
if (!filter_node_name) {
mirror_top_bs->implicit = true;
}
mirror_top_bs->total_sectors = bs->total_sectors;
mirror_top_bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
mirror_top_bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED;
bdrv_set_aio_context(mirror_top_bs, bdrv_get_aio_context(bs));
/* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
* it alive until block_job_create() succeeds even if bs has no parent. */
bdrv_ref(mirror_top_bs);
bdrv_drained_begin(bs);
bdrv_append(mirror_top_bs, bs, &local_err);
bdrv_drained_end(bs);
if (local_err) {
bdrv_unref(mirror_top_bs);
error_propagate(errp, local_err);
return;
}
/* Make sure that the source is not resized while the job is running */
s = block_job_create(job_id, driver, NULL, mirror_top_bs,
BLK_PERM_CONSISTENT_READ,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed,
creation_flags, cb, opaque, errp);
if (!s) {
goto fail;
}
/* The block job now has a reference to this node */
bdrv_unref(mirror_top_bs);
s->source = bs;
s->mirror_top_bs = mirror_top_bs;
/* No resize for the target either; while the mirror is still running, a
* consistent read isn't necessarily possible. We could possibly allow
* writes and graph modifications, though it would likely defeat the
* purpose of a mirror, so leave them blocked for now.
*
* In the case of active commit, things look a bit different, though,
* because the target is an already populated backing file in active use.
* We can allow anything except resize there.*/
target_is_backing = bdrv_chain_contains(bs, target);
target_graph_mod = (backing_mode != MIRROR_LEAVE_BACKING_CHAIN);
s->target = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE |
(target_graph_mod ? BLK_PERM_GRAPH_MOD : 0),
BLK_PERM_WRITE_UNCHANGED |
(target_is_backing ? BLK_PERM_CONSISTENT_READ |
BLK_PERM_WRITE |
BLK_PERM_GRAPH_MOD : 0));
ret = blk_insert_bs(s->target, target, errp);
if (ret < 0) {
goto fail;
}
if (is_mirror) {
/* XXX: Mirror target could be a NBD server of target QEMU in the case
* of non-shared block migration. To allow migration completion, we
* have to allow "inactivate" of the target BB. When that happens, we
* know the job is drained, and the vcpus are stopped, so no write
* operation will be performed. Block layer already has assertions to
* ensure that. */
blk_set_force_allow_inactivate(s->target);
}
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
s->on_target_error = on_target_error;
s->is_none_mode = is_none_mode;
s->backing_mode = backing_mode;
s->base = base;
s->granularity = granularity;
s->buf_size = ROUND_UP(buf_size, granularity);
s->unmap = unmap;
if (auto_complete) {
s->should_complete = true;
}
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
if (!s->dirty_bitmap) {
goto fail;
}
/* Required permissions are already taken with blk_new() */
block_job_add_bdrv(&s->common, "target", target, 0, BLK_PERM_ALL,
&error_abort);
/* In commit_active_start() all intermediate nodes disappear, so
* any jobs in them must be blocked */
if (target_is_backing) {
BlockDriverState *iter;
for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
/* XXX BLK_PERM_WRITE needs to be allowed so we don't block
* ourselves at s->base (if writes are blocked for a node, they are
* also blocked for its backing file). The other options would be a
* second filter driver above s->base (== target). */
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
errp);
if (ret < 0) {
goto fail;
}
}
}
trace_mirror_start(bs, s, opaque);
block_job_start(&s->common);
return;
fail:
if (s) {
/* Make sure this BDS does not go away until we have completed the graph
* changes below */
bdrv_ref(mirror_top_bs);
g_free(s->replaces);
blk_unref(s->target);
block_job_early_fail(&s->common);
}
bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
&error_abort);
bdrv_replace_node(mirror_top_bs, backing_bs(mirror_top_bs), &error_abort);
bdrv_unref(mirror_top_bs);
}
void stream_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, const char *backing_file_str,
int creation_flags, int64_t speed,
BlockdevOnError on_error, Error **errp)
{
StreamBlockJob *s;
BlockDriverState *iter;
bool bs_read_only;
if (bdrv_freeze_backing_chain(bs, base, errp) < 0) {
return;
}
/* Make sure that the image is opened in read-write mode */
bs_read_only = bdrv_is_read_only(bs);
if (bs_read_only) {
if (bdrv_reopen_set_read_only(bs, false, errp) != 0) {
bs_read_only = false;
goto fail;
}
}
/* Prevent concurrent jobs trying to modify the graph structure here, we
* already have our own plans. Also don't allow resize as the image size is
* queried only at the job start and then cached. */
s = block_job_create(job_id, &stream_job_driver, NULL, bs,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_GRAPH_MOD,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
BLK_PERM_WRITE,
speed, creation_flags, NULL, NULL, errp);
if (!s) {
goto fail;
}
/* Block all intermediate nodes between bs and base, because they will
* disappear from the chain after this operation. The streaming job reads
* every block only once, assuming that it doesn't change, so block writes
* and resizes. */
for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
&error_abort);
}
s->base = base;
s->backing_file_str = g_strdup(backing_file_str);
s->bs_read_only = bs_read_only;
s->chain_frozen = true;
s->on_error = on_error;
trace_stream_start(bs, base, s);
job_start(&s->common.job);
return;
fail:
if (bs_read_only) {
bdrv_reopen_set_read_only(bs, true, NULL);
}
bdrv_unfreeze_backing_chain(bs, base);
}
void commit_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, BlockDriverState *top,
int creation_flags, int64_t speed,
BlockdevOnError on_error, const char *backing_file_str,
const char *filter_node_name, Error **errp)
{
CommitBlockJob *s;
BlockDriverState *iter;
BlockDriverState *commit_top_bs = NULL;
Error *local_err = NULL;
int ret;
assert(top != bs);
if (top == base) {
error_setg(errp, "Invalid files for merge: top and base are the same");
return;
}
s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL,
speed, creation_flags, NULL, NULL, errp);
if (!s) {
return;
}
/* convert base to r/w, if necessary */
s->base_read_only = bdrv_is_read_only(base);
if (s->base_read_only) {
if (bdrv_reopen_set_read_only(base, false, errp) != 0) {
goto fail;
}
}
/* Insert commit_top block node above top, so we can block consistent read
* on the backing chain below it */
commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
errp);
if (commit_top_bs == NULL) {
goto fail;
}
if (!filter_node_name) {
commit_top_bs->implicit = true;
}
commit_top_bs->total_sectors = top->total_sectors;
bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(top));
bdrv_set_backing_hd(commit_top_bs, top, &local_err);
if (local_err) {
bdrv_unref(commit_top_bs);
commit_top_bs = NULL;
error_propagate(errp, local_err);
goto fail;
}
bdrv_replace_node(top, commit_top_bs, &local_err);
if (local_err) {
bdrv_unref(commit_top_bs);
commit_top_bs = NULL;
error_propagate(errp, local_err);
goto fail;
}
s->commit_top_bs = commit_top_bs;
bdrv_unref(commit_top_bs);
/* Block all nodes between top and base, because they will
* disappear from the chain after this operation. */
assert(bdrv_chain_contains(top, base));
for (iter = top; iter != base; iter = backing_bs(iter)) {
/* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
* at s->base (if writes are blocked for a node, they are also blocked
* for its backing file). The other options would be a second filter
* driver above s->base. */
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
errp);
if (ret < 0) {
goto fail;
}
}
if (bdrv_freeze_backing_chain(commit_top_bs, base, errp) < 0) {
goto fail;
}
s->chain_frozen = true;
ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
if (ret < 0) {
goto fail;
}
s->base = blk_new(BLK_PERM_CONSISTENT_READ
| BLK_PERM_WRITE
| BLK_PERM_RESIZE,
BLK_PERM_CONSISTENT_READ
| BLK_PERM_GRAPH_MOD
| BLK_PERM_WRITE_UNCHANGED);
ret = blk_insert_bs(s->base, base, errp);
if (ret < 0) {
goto fail;
}
s->base_bs = base;
/* Required permissions are already taken with block_job_add_bdrv() */
s->top = blk_new(0, BLK_PERM_ALL);
ret = blk_insert_bs(s->top, top, errp);
if (ret < 0) {
goto fail;
}
s->backing_file_str = g_strdup(backing_file_str);
s->on_error = on_error;
trace_commit_start(bs, base, top, s);
job_start(&s->common.job);
return;
fail:
if (s->chain_frozen) {
bdrv_unfreeze_backing_chain(commit_top_bs, base);
}
if (s->base) {
blk_unref(s->base);
}
if (s->top) {
blk_unref(s->top);
}
job_early_fail(&s->common.job);
/* commit_top_bs has to be replaced after deleting the block job,
* otherwise this would fail because of lack of permissions. */
if (commit_top_bs) {
bdrv_replace_node(commit_top_bs, top, &error_abort);
}
}
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockErrorAction on_error, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
CommitBlockJob *s;
BlockReopenQueue *reopen_queue = NULL;
int orig_overlay_flags;
int orig_base_flags;
BlockDriverState *overlay_bs;
Error *local_err = NULL;
if ((on_error == BLOCK_ERR_STOP_ANY ||
on_error == BLOCK_ERR_STOP_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
return;
}
/* Once we support top == active layer, remove this check */
if (top == bs) {
error_set(errp, QERR_TOP_IS_ACTIVE);
return;
}
if (top == base) {
error_set(errp, QERR_TOP_AND_BASE_IDENTICAL);
return;
}
overlay_bs = bdrv_find_overlay(bs, top);
if (overlay_bs == NULL) {
error_set(errp, QERR_TOP_NOT_FOUND, top->filename);
return;
}
orig_base_flags = bdrv_get_flags(base);
orig_overlay_flags = bdrv_get_flags(overlay_bs);
/* convert base & overlay_bs to r/w, if necessary */
if (!(orig_base_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, base,
orig_base_flags | BDRV_O_RDWR);
}
if (!(orig_overlay_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
orig_overlay_flags | BDRV_O_RDWR);
}
if (reopen_queue) {
bdrv_reopen_multiple(reopen_queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
return;
}
}
s = block_job_create(&commit_job_type, bs, speed, cb, opaque);
if (!s) {
error_set(errp, QERR_DEVICE_IN_USE, bs->device_name);
return;
}
s->base = base;
s->top = top;
s->active = bs;
s->base_flags = orig_base_flags;
s->orig_overlay_flags = orig_overlay_flags;
s->on_error = on_error;
s->common.co = qemu_coroutine_create(commit_run);
trace_commit_start(bs, base, top, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
}
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
CommitBlockJob *s;
BlockReopenQueue *reopen_queue = NULL;
int orig_overlay_flags;
int orig_base_flags;
BlockDriverState *overlay_bs;
Error *local_err = NULL;
if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
return;
}
/* Once we support top == active layer, remove this check */
if (top == bs) {
error_setg(errp,
"Top image as the active layer is currently unsupported");
return;
}
if (top == base) {
error_setg(errp, "Invalid files for merge: top and base are the same");
return;
}
overlay_bs = bdrv_find_overlay(bs, top);
if (overlay_bs == NULL) {
error_setg(errp, "Could not find overlay image for %s:", top->filename);
return;
}
orig_base_flags = bdrv_get_flags(base);
orig_overlay_flags = bdrv_get_flags(overlay_bs);
/* convert base & overlay_bs to r/w, if necessary */
if (!(orig_base_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, base,
orig_base_flags | BDRV_O_RDWR);
}
if (!(orig_overlay_flags & BDRV_O_RDWR)) {
reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
orig_overlay_flags | BDRV_O_RDWR);
}
if (reopen_queue) {
bdrv_reopen_multiple(reopen_queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
return;
}
}
s = block_job_create(&commit_job_type, bs, speed, cb, opaque, errp);
if (!s) {
return;
}
s->base = base;
s->top = top;
s->active = bs;
s->base_flags = orig_base_flags;
s->orig_overlay_flags = orig_overlay_flags;
s->on_error = on_error;
s->common.co = qemu_coroutine_create(commit_run);
trace_commit_start(bs, base, top, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
}
