unsigned long *in_flight_bitmap;
int in_flight;
int64_t bytes_in_flight;
- QTAILQ_HEAD(MirrorOpList, MirrorOp) ops_in_flight;
+ QTAILQ_HEAD(, MirrorOp) ops_in_flight;
int ret;
bool unmap;
int target_cluster_size;
int max_iov;
bool initial_zeroing_ongoing;
int in_active_write_counter;
+ bool prepared;
+ bool in_drain;
} MirrorBlockJob;
typedef struct MirrorBDSOpaque {
MirrorBlockJob *job;
+ bool stop;
} MirrorBDSOpaque;
struct MirrorOp {
{
MirrorBlockJob *s = op->s;
- aio_context_acquire(blk_get_aio_context(s->common.blk));
if (ret < 0) {
BlockErrorAction action;
s->ret = ret;
}
}
+
mirror_iteration_done(op, ret);
- aio_context_release(blk_get_aio_context(s->common.blk));
}
static void coroutine_fn mirror_read_complete(MirrorOp *op, int ret)
{
MirrorBlockJob *s = op->s;
- aio_context_acquire(blk_get_aio_context(s->common.blk));
if (ret < 0) {
BlockErrorAction action;
}
mirror_iteration_done(op, ret);
- } else {
- ret = blk_co_pwritev(s->target, op->offset,
- op->qiov.size, &op->qiov, 0);
- mirror_write_complete(op, ret);
+ return;
}
- aio_context_release(blk_get_aio_context(s->common.blk));
+
+ ret = blk_co_pwritev(s->target, op->offset, op->qiov.size, &op->qiov, 0);
+ mirror_write_complete(op, ret);
}
/* Clip bytes relative to offset to not exceed end-of-file */
return ret;
}
-static inline void mirror_wait_for_any_operation(MirrorBlockJob *s, bool active)
+static inline void coroutine_fn
+mirror_wait_for_any_operation(MirrorBlockJob *s, bool active)
{
MirrorOp *op;
abort();
}
-static inline void mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s)
+static inline void coroutine_fn
+mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s)
{
/* Only non-active operations use up in-flight slots */
mirror_wait_for_any_operation(s, false);
* mirror_resume() because mirror_run() will begin iterating again
* when the job is resumed.
*/
-static void mirror_wait_for_all_io(MirrorBlockJob *s)
+static void coroutine_fn mirror_wait_for_all_io(MirrorBlockJob *s)
{
while (s->in_flight > 0) {
mirror_wait_for_free_in_flight_slot(s);
}
}
-typedef struct {
- int ret;
-} MirrorExitData;
-
-static void mirror_exit(Job *job, void *opaque)
+/**
+ * mirror_exit_common: handle both abort() and prepare() cases.
+ * for .prepare, returns 0 on success and -errno on failure.
+ * for .abort cases, denoted by abort = true, MUST return 0.
+ */
+static int mirror_exit_common(Job *job)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common.job);
BlockJob *bjob = &s->common;
- MirrorExitData *data = opaque;
MirrorBDSOpaque *bs_opaque = s->mirror_top_bs->opaque;
AioContext *replace_aio_context = NULL;
BlockDriverState *src = s->mirror_top_bs->backing->bs;
BlockDriverState *target_bs = blk_bs(s->target);
BlockDriverState *mirror_top_bs = s->mirror_top_bs;
Error *local_err = NULL;
+ bool abort = job->ret < 0;
+ int ret = 0;
+
+ if (s->prepared) {
+ return 0;
+ }
+ s->prepared = true;
+
+ if (bdrv_chain_contains(src, target_bs)) {
+ bdrv_unfreeze_backing_chain(mirror_top_bs, target_bs);
+ }
bdrv_release_dirty_bitmap(src, s->dirty_bitmap);
- /* Make sure that the source BDS doesn't go away before we called
- * job_completed(). */
+ /* Make sure that the source BDS doesn't go away during bdrv_replace_node,
+ * before we can call bdrv_drained_end */
bdrv_ref(src);
bdrv_ref(mirror_top_bs);
bdrv_ref(target_bs);
/* We don't access the source any more. Dropping any WRITE/RESIZE is
* required before it could become a backing file of target_bs. */
- bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
- &error_abort);
- if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
+ bs_opaque->stop = true;
+ bdrv_child_refresh_perms(mirror_top_bs, mirror_top_bs->backing,
+ &error_abort);
+ if (!abort && s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
BlockDriverState *backing = s->is_none_mode ? src : s->base;
if (backing_bs(target_bs) != backing) {
bdrv_set_backing_hd(target_bs, backing, &local_err);
if (local_err) {
error_report_err(local_err);
- data->ret = -EPERM;
+ ret = -EPERM;
}
}
}
aio_context_acquire(replace_aio_context);
}
- if (s->should_complete && data->ret == 0) {
- BlockDriverState *to_replace = src;
- if (s->to_replace) {
- to_replace = s->to_replace;
- }
+ if (s->should_complete && !abort) {
+ BlockDriverState *to_replace = s->to_replace ?: src;
+ bool ro = bdrv_is_read_only(to_replace);
- if (bdrv_get_flags(target_bs) != bdrv_get_flags(to_replace)) {
- bdrv_reopen(target_bs, bdrv_get_flags(to_replace), NULL);
+ if (ro != bdrv_is_read_only(target_bs)) {
+ bdrv_reopen_set_read_only(target_bs, ro, NULL);
}
/* The mirror job has no requests in flight any more, but we need to
* drain potential other users of the BDS before changing the graph. */
+ assert(s->in_drain);
bdrv_drained_begin(target_bs);
bdrv_replace_node(to_replace, target_bs, &local_err);
bdrv_drained_end(target_bs);
if (local_err) {
error_report_err(local_err);
- data->ret = -EPERM;
+ ret = -EPERM;
}
}
if (s->to_replace) {
g_free(s->replaces);
bdrv_unref(target_bs);
- /* Remove the mirror filter driver from the graph. Before this, get rid of
+ /*
+ * Remove the mirror filter driver from the graph. Before this, get rid of
* the blockers on the intermediate nodes so that the resulting state is
- * valid. Also give up permissions on mirror_top_bs->backing, which might
- * block the removal. */
+ * valid.
+ */
block_job_remove_all_bdrv(bjob);
- 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);
/* We just changed the BDS the job BB refers to (with either or both of the
blk_insert_bs(bjob->blk, mirror_top_bs, &error_abort);
bs_opaque->job = NULL;
- job_completed(job, data->ret);
- g_free(data);
bdrv_drained_end(src);
+ s->in_drain = false;
bdrv_unref(mirror_top_bs);
bdrv_unref(src);
+
+ return ret;
+}
+
+static int mirror_prepare(Job *job)
+{
+ return mirror_exit_common(job);
+}
+
+static void mirror_abort(Job *job)
+{
+ int ret = mirror_exit_common(job);
+ assert(ret == 0);
}
-static void mirror_throttle(MirrorBlockJob *s)
+static void coroutine_fn mirror_throttle(MirrorBlockJob *s)
{
int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
static int coroutine_fn mirror_run(Job *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common.job);
- MirrorExitData *data;
BlockDriverState *bs = s->mirror_top_bs->backing->bs;
BlockDriverState *target_bs = blk_bs(s->target);
bool need_drain = true;
*/
trace_mirror_before_drain(s, cnt);
+ s->in_drain = true;
bdrv_drained_begin(bs);
cnt = bdrv_get_dirty_count(s->dirty_bitmap);
if (cnt > 0 || mirror_flush(s) < 0) {
bdrv_drained_end(bs);
+ s->in_drain = false;
continue;
}
g_free(s->in_flight_bitmap);
bdrv_dirty_iter_free(s->dbi);
- data = g_malloc(sizeof(*data));
- data->ret = ret;
-
if (need_drain) {
+ s->in_drain = true;
bdrv_drained_begin(bs);
}
- job_defer_to_main_loop(&s->common.job, mirror_exit, data);
return ret;
}
job_enter(job);
}
-static void mirror_pause(Job *job)
+static void coroutine_fn mirror_pause(Job *job)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common.job);
static bool mirror_drained_poll(BlockJob *job)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
- return !!s->in_flight;
-}
-static void mirror_attached_aio_context(BlockJob *job, AioContext *new_context)
-{
- MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
+ /* If the job isn't paused nor cancelled, we can't be sure that it won't
+ * issue more requests. We make an exception if we've reached this point
+ * from one of our own drain sections, to avoid a deadlock waiting for
+ * ourselves.
+ */
+ if (!s->common.job.paused && !s->common.job.cancelled && !s->in_drain) {
+ return true;
+ }
- blk_set_aio_context(s->target, new_context);
+ return !!s->in_flight;
}
static void mirror_drain(BlockJob *job)
.user_resume = block_job_user_resume,
.drain = block_job_drain,
.run = mirror_run,
+ .prepare = mirror_prepare,
+ .abort = mirror_abort,
.pause = mirror_pause,
.complete = mirror_complete,
},
.drained_poll = mirror_drained_poll,
- .attached_aio_context = mirror_attached_aio_context,
.drain = mirror_drain,
};
.user_resume = block_job_user_resume,
.drain = block_job_drain,
.run = mirror_run,
+ .prepare = mirror_prepare,
+ .abort = mirror_abort,
.pause = mirror_pause,
.complete = mirror_complete,
},
.drained_poll = mirror_drained_poll,
- .attached_aio_context = mirror_attached_aio_context,
.drain = mirror_drain,
};
-static void do_sync_target_write(MirrorBlockJob *job, MirrorMethod method,
- uint64_t offset, uint64_t bytes,
- QEMUIOVector *qiov, int flags)
+static void coroutine_fn
+do_sync_target_write(MirrorBlockJob *job, MirrorMethod method,
+ uint64_t offset, uint64_t bytes,
+ QEMUIOVector *qiov, int flags)
{
- BdrvDirtyBitmapIter *iter;
QEMUIOVector target_qiov;
- uint64_t dirty_offset;
- int dirty_bytes;
+ uint64_t dirty_offset = offset;
+ uint64_t dirty_bytes;
if (qiov) {
qemu_iovec_init(&target_qiov, qiov->niov);
}
- iter = bdrv_dirty_iter_new(job->dirty_bitmap);
- bdrv_set_dirty_iter(iter, offset);
-
while (true) {
bool valid_area;
int ret;
bdrv_dirty_bitmap_lock(job->dirty_bitmap);
- valid_area = bdrv_dirty_iter_next_area(iter, offset + bytes,
- &dirty_offset, &dirty_bytes);
+ dirty_bytes = MIN(offset + bytes - dirty_offset, INT_MAX);
+ valid_area = bdrv_dirty_bitmap_next_dirty_area(job->dirty_bitmap,
+ &dirty_offset,
+ &dirty_bytes);
if (!valid_area) {
bdrv_dirty_bitmap_unlock(job->dirty_bitmap);
break;
break;
}
}
+
+ dirty_offset += dirty_bytes;
}
- bdrv_dirty_iter_free(iter);
if (qiov) {
qemu_iovec_destroy(&target_qiov);
}
NULL, 0);
}
-static void bdrv_mirror_top_refresh_filename(BlockDriverState *bs, QDict *opts)
+static void bdrv_mirror_top_refresh_filename(BlockDriverState *bs)
{
if (bs->backing == NULL) {
/* we can be here after failed bdrv_attach_child in
* bdrv_set_backing_hd */
return;
}
- bdrv_refresh_filename(bs->backing->bs);
pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
bs->backing->bs->filename);
}
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
{
+ MirrorBDSOpaque *s = bs->opaque;
+
+ if (s->stop) {
+ /*
+ * If the job is to be stopped, we do not need to forward
+ * anything to the real image.
+ */
+ *nperm = 0;
+ *nshared = BLK_PERM_ALL;
+ return;
+ }
+
/* Must be able to forward guest writes to the real image */
*nperm = 0;
if (perm & BLK_PERM_WRITE) {
.bdrv_child_perm = bdrv_mirror_top_child_perm,
};
-static void mirror_start_job(const char *job_id, BlockDriverState *bs,
+static BlockJob *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,
if (buf_size < 0) {
error_setg(errp, "Invalid parameter 'buf-size'");
- return;
+ return NULL;
}
if (buf_size == 0) {
if (bs == target) {
error_setg(errp, "Can't mirror node into itself");
- return;
+ return NULL;
}
/* In the case of active commit, add dummy driver to provide consistent
mirror_top_bs = bdrv_new_open_driver(&bdrv_mirror_top, filter_node_name,
BDRV_O_RDWR, errp);
if (mirror_top_bs == NULL) {
- return;
+ return NULL;
}
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;
+ mirror_top_bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
+ BDRV_REQ_NO_FALLBACK;
bs_opaque = g_new0(MirrorBDSOpaque, 1);
mirror_top_bs->opaque = bs_opaque;
- 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. */
if (local_err) {
bdrv_unref(mirror_top_bs);
error_propagate(errp, local_err);
- return;
+ return NULL;
}
/* Make sure that the source is not resized while the job is running */
* 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 |
+ s->target = blk_new(s->common.job.aio_context,
+ 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 |
* ensure that. */
blk_set_force_allow_inactivate(s->target);
}
+ blk_set_allow_aio_context_change(s->target, true);
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
goto fail;
}
+ ret = block_job_add_bdrv(&s->common, "source", bs, 0,
+ BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE |
+ BLK_PERM_CONSISTENT_READ,
+ errp);
+ if (ret < 0) {
+ goto fail;
+ }
+
/* Required permissions are already taken with blk_new() */
block_job_add_bdrv(&s->common, "target", target, 0, BLK_PERM_ALL,
&error_abort);
goto fail;
}
}
+
+ if (bdrv_freeze_backing_chain(mirror_top_bs, target, errp) < 0) {
+ goto fail;
+ }
}
QTAILQ_INIT(&s->ops_in_flight);
trace_mirror_start(bs, s, opaque);
job_start(&s->common.job);
- return;
+
+ return &s->common;
fail:
if (s) {
g_free(s->replaces);
blk_unref(s->target);
bs_opaque->job = NULL;
+ if (s->dirty_bitmap) {
+ bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
+ }
job_early_fail(&s->common.job);
}
- bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
- &error_abort);
+ bs_opaque->stop = true;
+ bdrv_child_refresh_perms(mirror_top_bs, mirror_top_bs->backing,
+ &error_abort);
bdrv_replace_node(mirror_top_bs, backing_bs(mirror_top_bs), &error_abort);
bdrv_unref(mirror_top_bs);
+
+ return NULL;
}
void mirror_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *target, const char *replaces,
- int64_t speed, uint32_t granularity, int64_t buf_size,
+ int creation_flags, int64_t speed,
+ uint32_t granularity, int64_t buf_size,
MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
}
is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
base = mode == MIRROR_SYNC_MODE_TOP ? backing_bs(bs) : NULL;
- mirror_start_job(job_id, bs, JOB_DEFAULT, target, replaces,
+ mirror_start_job(job_id, bs, creation_flags, target, replaces,
speed, granularity, buf_size, backing_mode,
on_source_error, on_target_error, unmap, NULL, NULL,
&mirror_job_driver, is_none_mode, base, false,
filter_node_name, true, copy_mode, errp);
}
-void commit_active_start(const char *job_id, BlockDriverState *bs,
- BlockDriverState *base, int creation_flags,
- int64_t speed, BlockdevOnError on_error,
- const char *filter_node_name,
- BlockCompletionFunc *cb, void *opaque,
- bool auto_complete, Error **errp)
+BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
+ BlockDriverState *base, int creation_flags,
+ int64_t speed, BlockdevOnError on_error,
+ const char *filter_node_name,
+ BlockCompletionFunc *cb, void *opaque,
+ bool auto_complete, Error **errp)
{
- int orig_base_flags;
+ bool base_read_only;
Error *local_err = NULL;
+ BlockJob *ret;
- orig_base_flags = bdrv_get_flags(base);
+ base_read_only = bdrv_is_read_only(base);
- if (bdrv_reopen(base, bs->open_flags, errp)) {
- return;
+ if (base_read_only) {
+ if (bdrv_reopen_set_read_only(base, false, errp) < 0) {
+ return NULL;
+ }
}
- mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0,
+ ret = mirror_start_job(
+ job_id, bs, creation_flags, base, NULL, speed, 0, 0,
MIRROR_LEAVE_BACKING_CHAIN,
on_error, on_error, true, cb, opaque,
&commit_active_job_driver, false, base, auto_complete,
goto error_restore_flags;
}
- return;
+ return ret;
error_restore_flags:
/* ignore error and errp for bdrv_reopen, because we want to propagate
* the original error */
- bdrv_reopen(base, orig_base_flags, NULL);
- return;
+ if (base_read_only) {
+ bdrv_reopen_set_read_only(base, true, NULL);
+ }
+ return NULL;
}
projects / qemu.git / blobdiff