block: let mirror blockjob run in BDS AioContext

The mirror block job must run in the BlockDriverState AioContext so that
it works with dataplane.

Acquire the AioContext in blockdev.c so starting the block job is safe.

Note that to_replace is treated separately from other BlockDriverStates
in that it does not need to be in the same AioContext.  Explicitly
acquire/release to_replace's AioContext when accessing it.

The completion code in block/mirror.c must perform BDS graph
manipulation and bdrv_reopen() from the main loop.  Use
block_job_defer_to_main_loop() to achieve that.

The bdrv_drain_all() call is not allowed outside the main loop since it
could lead to lock ordering problems.  Use bdrv_drain(bs) instead
because we have acquired the AioContext so nothing else can sneak in
I/O.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-id: 1413889440-32577-10-git-send-email-stefanha@redhat.com
This commit is contained in:
Stefan Hajnoczi 2014-10-21 12:03:58 +01:00
parent f3e69beb94
commit 5a7e7a0bad
3 changed files with 97 additions and 39 deletions

13
block.c
View File

@ -5850,13 +5850,19 @@ bool bdrv_is_first_non_filter(BlockDriverState *candidate)
BlockDriverState *check_to_replace_node(const char *node_name, Error **errp)
{
BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
AioContext *aio_context;
if (!to_replace_bs) {
error_setg(errp, "Node name '%s' not found", node_name);
return NULL;
}
aio_context = bdrv_get_aio_context(to_replace_bs);
aio_context_acquire(aio_context);
if (bdrv_op_is_blocked(to_replace_bs, BLOCK_OP_TYPE_REPLACE, errp)) {
return NULL;
to_replace_bs = NULL;
goto out;
}
/* We don't want arbitrary node of the BDS chain to be replaced only the top
@ -5866,9 +5872,12 @@ BlockDriverState *check_to_replace_node(const char *node_name, Error **errp)
*/
if (!bdrv_is_first_non_filter(to_replace_bs)) {
error_setg(errp, "Only top most non filter can be replaced");
return NULL;
to_replace_bs = NULL;
goto out;
}
out:
aio_context_release(aio_context);
return to_replace_bs;
}

View File

@ -321,9 +321,56 @@ static void mirror_drain(MirrorBlockJob *s)
}
}
typedef struct {
int ret;
} MirrorExitData;
static void mirror_exit(BlockJob *job, void *opaque)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
if (s->to_replace) {
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
}
if (s->should_complete && data->ret == 0) {
BlockDriverState *to_replace = s->common.bs;
if (s->to_replace) {
to_replace = s->to_replace;
}
if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
}
bdrv_swap(s->target, to_replace);
if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
/* drop the bs loop chain formed by the swap: break the loop then
* trigger the unref from the top one */
BlockDriverState *p = s->base->backing_hd;
bdrv_set_backing_hd(s->base, NULL);
bdrv_unref(p);
}
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
if (replace_aio_context) {
aio_context_release(replace_aio_context);
}
g_free(s->replaces);
bdrv_unref(s->target);
block_job_completed(&s->common, data->ret);
g_free(data);
}
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
MirrorExitData *data;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, sectors_per_chunk, length;
uint64_t last_pause_ns;
@ -479,7 +526,7 @@ static void coroutine_fn mirror_run(void *opaque)
* mirror_populate runs.
*/
trace_mirror_before_drain(s, cnt);
bdrv_drain_all();
bdrv_drain(bs);
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
}
@ -520,31 +567,10 @@ immediate_exit:
g_free(s->in_flight_bitmap);
bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
bdrv_iostatus_disable(s->target);
if (s->should_complete && ret == 0) {
BlockDriverState *to_replace = s->common.bs;
if (s->to_replace) {
to_replace = s->to_replace;
}
if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
}
bdrv_swap(s->target, to_replace);
if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
/* drop the bs loop chain formed by the swap: break the loop then
* trigger the unref from the top one */
BlockDriverState *p = s->base->backing_hd;
bdrv_set_backing_hd(s->base, NULL);
bdrv_unref(p);
}
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
g_free(s->replaces);
bdrv_unref(s->target);
block_job_completed(&s->common, ret);
data = g_malloc(sizeof(*data));
data->ret = ret;
block_job_defer_to_main_loop(&s->common, mirror_exit, data);
}
static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
@ -584,16 +610,23 @@ static void mirror_complete(BlockJob *job, Error **errp)
/* check the target bs is not blocked and block all operations on it */
if (s->replaces) {
AioContext *replace_aio_context;
s->to_replace = check_to_replace_node(s->replaces, &local_err);
if (!s->to_replace) {
error_propagate(errp, local_err);
return;
}
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
bdrv_ref(s->to_replace);
aio_context_release(replace_aio_context);
}
s->should_complete = true;

View File

@ -2245,6 +2245,7 @@ void qmp_drive_mirror(const char *device, const char *target,
{
BlockDriverState *bs;
BlockDriverState *source, *target_bs;
AioContext *aio_context;
BlockDriver *drv = NULL;
Error *local_err = NULL;
QDict *options = NULL;
@ -2287,9 +2288,12 @@ void qmp_drive_mirror(const char *device, const char *target,
return;
}
aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
if (!bdrv_is_inserted(bs)) {
error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
return;
goto out;
}
if (!has_format) {
@ -2299,12 +2303,12 @@ void qmp_drive_mirror(const char *device, const char *target,
drv = bdrv_find_format(format);
if (!drv) {
error_set(errp, QERR_INVALID_BLOCK_FORMAT, format);
return;
goto out;
}
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR, errp)) {
return;
goto out;
}
flags = bs->open_flags | BDRV_O_RDWR;
@ -2319,29 +2323,36 @@ void qmp_drive_mirror(const char *device, const char *target,
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
return;
goto out;
}
if (has_replaces) {
BlockDriverState *to_replace_bs;
AioContext *replace_aio_context;
int64_t replace_size;
if (!has_node_name) {
error_setg(errp, "a node-name must be provided when replacing a"
" named node of the graph");
return;
goto out;
}
to_replace_bs = check_to_replace_node(replaces, &local_err);
if (!to_replace_bs) {
error_propagate(errp, local_err);
return;
goto out;
}
if (size != bdrv_getlength(to_replace_bs)) {
replace_aio_context = bdrv_get_aio_context(to_replace_bs);
aio_context_acquire(replace_aio_context);
replace_size = bdrv_getlength(to_replace_bs);
aio_context_release(replace_aio_context);
if (size != replace_size) {
error_setg(errp, "cannot replace image with a mirror image of "
"different size");
return;
goto out;
}
}
@ -2370,7 +2381,7 @@ void qmp_drive_mirror(const char *device, const char *target,
if (local_err) {
error_propagate(errp, local_err);
return;
goto out;
}
if (has_node_name) {
@ -2386,9 +2397,11 @@ void qmp_drive_mirror(const char *device, const char *target,
flags | BDRV_O_NO_BACKING, drv, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return;
goto out;
}
bdrv_set_aio_context(target_bs, aio_context);
/* pass the node name to replace to mirror start since it's loose coupling
* and will allow to check whether the node still exist at mirror completion
*/
@ -2400,8 +2413,11 @@ void qmp_drive_mirror(const char *device, const char *target,
if (local_err != NULL) {
bdrv_unref(target_bs);
error_propagate(errp, local_err);
return;
goto out;
}
out:
aio_context_release(aio_context);
}
/* Get the block job for a given device name and acquire its AioContext */