qemu/blockjob.c

550 lines
16 KiB
C
Raw Normal View History

/*
* QEMU System Emulator block driver
*
* Copyright (c) 2011 IBM Corp.
* Copyright (c) 2012 Red Hat, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/block.h"
#include "block/blockjob_int.h"
#include "block/block_int.h"
#include "block/trace.h"
#include "sysemu/block-backend.h"
#include "qapi/error.h"
#include "qapi/qapi-events-block-core.h"
#include "qapi/qmp/qerror.h"
#include "qemu/coroutine.h"
#include "qemu/main-loop.h"
#include "qemu/timer.h"
/*
* The block job API is composed of two categories of functions.
*
* The first includes functions used by the monitor. The monitor is
* peculiar in that it accesses the block job list with block_job_get, and
* therefore needs consistency across block_job_get and the actual operation
* (e.g. block_job_set_speed). The consistency is achieved with
* aio_context_acquire/release. These functions are declared in blockjob.h.
*
* The second includes functions used by the block job drivers and sometimes
* by the core block layer. These do not care about locking, because the
* whole coroutine runs under the AioContext lock, and are declared in
* blockjob_int.h.
*/
static bool is_block_job(Job *job)
{
return job_type(job) == JOB_TYPE_BACKUP ||
job_type(job) == JOB_TYPE_COMMIT ||
job_type(job) == JOB_TYPE_MIRROR ||
job_type(job) == JOB_TYPE_STREAM;
}
BlockJob *block_job_next(BlockJob *bjob)
{
Job *job = bjob ? &bjob->job : NULL;
do {
job = job_next(job);
} while (job && !is_block_job(job));
return job ? container_of(job, BlockJob, job) : NULL;
}
BlockJob *block_job_get(const char *id)
{
Job *job = job_get(id);
if (job && is_block_job(job)) {
return container_of(job, BlockJob, job);
} else {
return NULL;
}
}
void block_job_free(Job *job)
{
BlockJob *bjob = container_of(job, BlockJob, job);
block_job_remove_all_bdrv(bjob);
blk_unref(bjob->blk);
ratelimit_destroy(&bjob->limit);
error_free(bjob->blocker);
}
static char *child_job_get_parent_desc(BdrvChild *c)
{
BlockJob *job = c->opaque;
return g_strdup_printf("%s job '%s'", job_type_str(&job->job), job->job.id);
}
static void child_job_drained_begin(BdrvChild *c)
{
BlockJob *job = c->opaque;
job_pause(&job->job);
}
static bool child_job_drained_poll(BdrvChild *c)
{
BlockJob *bjob = c->opaque;
Job *job = &bjob->job;
const BlockJobDriver *drv = block_job_driver(bjob);
/* An inactive or completed job doesn't have any pending requests. Jobs
* with !job->busy are either already paused or have a pause point after
* being reentered, so no job driver code will run before they pause. */
if (!job->busy || job_is_completed(job)) {
return false;
}
/* Otherwise, assume that it isn't fully stopped yet, but allow the job to
* override this assumption. */
if (drv->drained_poll) {
return drv->drained_poll(bjob);
} else {
return true;
}
}
block: Do not poll in bdrv_do_drained_end() We should never poll anywhere in bdrv_do_drained_end() (including its recursive callees like bdrv_drain_invoke()), because it does not cope well with graph changes. In fact, it has been written based on the postulation that no graph changes will happen in it. Instead, the callers that want to poll must poll, i.e. all currently globally available wrappers: bdrv_drained_end(), bdrv_subtree_drained_end(), bdrv_unapply_subtree_drain(), and bdrv_drain_all_end(). Graph changes there do not matter. They can poll simply by passing a pointer to a drained_end_counter and wait until it reaches 0. This patch also adds a non-polling global wrapper for bdrv_do_drained_end() that takes a drained_end_counter pointer. We need such a variant because now no function called anywhere from bdrv_do_drained_end() must poll. This includes BdrvChildRole.drained_end(), which already must not poll according to its interface documentation, but bdrv_child_cb_drained_end() just violates that by invoking bdrv_drained_end() (which does poll). Therefore, BdrvChildRole.drained_end() must take a *drained_end_counter parameter, which bdrv_child_cb_drained_end() can pass on to the new bdrv_drained_end_no_poll() function. Note that we now have a pattern of all drained_end-related functions either polling or receiving a *drained_end_counter to let the caller poll based on that. A problem with a single poll loop is that when the drained section in bdrv_set_aio_context_ignore() ends, some nodes in the subgraph may be in the old contexts, while others are in the new context already. To let the collective poll in bdrv_drained_end() work correctly, we must not hold a lock to the old context, so that the old context can make progress in case it is different from the current context. (In the process, remove the comment saying that the current context is always the old context, because it is wrong.) In all other places, all nodes in a subtree must be in the same context, so we can just poll that. The exception of course is bdrv_drain_all_end(), but that always runs in the main context, so we can just poll NULL (like bdrv_drain_all_begin() does). Signed-off-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2019-07-19 12:26:14 +03:00
static void child_job_drained_end(BdrvChild *c, int *drained_end_counter)
{
BlockJob *job = c->opaque;
job_resume(&job->job);
}
static bool child_job_can_set_aio_ctx(BdrvChild *c, AioContext *ctx,
GSList **ignore, Error **errp)
{
BlockJob *job = c->opaque;
GSList *l;
for (l = job->nodes; l; l = l->next) {
BdrvChild *sibling = l->data;
if (!bdrv_child_can_set_aio_context(sibling, ctx, ignore, errp)) {
return false;
}
}
return true;
}
static void child_job_set_aio_ctx(BdrvChild *c, AioContext *ctx,
GSList **ignore)
{
BlockJob *job = c->opaque;
GSList *l;
for (l = job->nodes; l; l = l->next) {
BdrvChild *sibling = l->data;
if (g_slist_find(*ignore, sibling)) {
continue;
}
*ignore = g_slist_prepend(*ignore, sibling);
bdrv_set_aio_context_ignore(sibling->bs, ctx, ignore);
}
job->job.aio_context = ctx;
}
static AioContext *child_job_get_parent_aio_context(BdrvChild *c)
{
BlockJob *job = c->opaque;
return job->job.aio_context;
}
static const BdrvChildClass child_job = {
.get_parent_desc = child_job_get_parent_desc,
.drained_begin = child_job_drained_begin,
.drained_poll = child_job_drained_poll,
.drained_end = child_job_drained_end,
.can_set_aio_ctx = child_job_can_set_aio_ctx,
.set_aio_ctx = child_job_set_aio_ctx,
.stay_at_node = true,
.get_parent_aio_context = child_job_get_parent_aio_context,
};
void block_job_remove_all_bdrv(BlockJob *job)
{
/*
* bdrv_root_unref_child() may reach child_job_[can_]set_aio_ctx(),
* which will also traverse job->nodes, so consume the list one by
* one to make sure that such a concurrent access does not attempt
* to process an already freed BdrvChild.
*/
while (job->nodes) {
GSList *l = job->nodes;
BdrvChild *c = l->data;
job->nodes = l->next;
bdrv_op_unblock_all(c->bs, job->blocker);
bdrv_root_unref_child(c);
g_slist_free_1(l);
}
}
bool block_job_has_bdrv(BlockJob *job, BlockDriverState *bs)
{
GSList *el;
for (el = job->nodes; el; el = el->next) {
BdrvChild *c = el->data;
if (c->bs == bs) {
return true;
}
}
return false;
}
int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
uint64_t perm, uint64_t shared_perm, Error **errp)
{
BdrvChild *c;
blockjob: Fix crash with IOthread when block commit after snapshot Currently, if guest has workloads, IO thread will acquire aio_context lock before do io_submit, it leads to segmentfault when do block commit after snapshot. Just like below: Program received signal SIGSEGV, Segmentation fault. [Switching to Thread 0x7f7c7d91f700 (LWP 99907)] 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437 1437 ../block/mirror.c: No such file or directory. (gdb) p s->job $17 = (MirrorBlockJob *) 0x0 (gdb) p s->stop $18 = false Call trace of IO thread: 0 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437 1 0x00005576d0f7f3ab in bdrv_driver_pwritev at ../block/io.c:1174 2 0x00005576d0f8139d in bdrv_aligned_pwritev at ../block/io.c:1988 3 0x00005576d0f81b65 in bdrv_co_pwritev_part at ../block/io.c:2156 4 0x00005576d0f8e6b7 in blk_do_pwritev_part at ../block/block-backend.c:1260 5 0x00005576d0f8e84d in blk_aio_write_entry at ../block/block-backend.c:1476 ... Switch to qemu main thread: 0 0x00007f903be704ed in __lll_lock_wait at /lib/../lib64/libpthread.so.0 1 0x00007f903be6bde6 in _L_lock_941 at /lib/../lib64/libpthread.so.0 2 0x00007f903be6bcdf in pthread_mutex_lock at /lib/../lib64/libpthread.so.0 3 0x0000564b21456889 in qemu_mutex_lock_impl at ../util/qemu-thread-posix.c:79 4 0x0000564b213af8a5 in block_job_add_bdrv at ../blockjob.c:224 5 0x0000564b213b00ad in block_job_create at ../blockjob.c:440 6 0x0000564b21357c0a in mirror_start_job at ../block/mirror.c:1622 7 0x0000564b2135a9af in commit_active_start at ../block/mirror.c:1867 8 0x0000564b2133d132 in qmp_block_commit at ../blockdev.c:2768 9 0x0000564b2141fef3 in qmp_marshal_block_commit at qapi/qapi-commands-block-core.c:346 10 0x0000564b214503c9 in do_qmp_dispatch_bh at ../qapi/qmp-dispatch.c:110 11 0x0000564b21451996 in aio_bh_poll at ../util/async.c:164 12 0x0000564b2146018e in aio_dispatch at ../util/aio-posix.c:381 13 0x0000564b2145187e in aio_ctx_dispatch at ../util/async.c:306 14 0x00007f9040239049 in g_main_context_dispatch at /lib/../lib64/libglib-2.0.so.0 15 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:232 16 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:255 17 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:531 18 0x0000564b212304e1 in qemu_main_loop at ../softmmu/runstate.c:721 19 0x0000564b20f7975e in main at ../softmmu/main.c:50 In IO thread when do bdrv_mirror_top_pwritev, the job is NULL, and stop field is false, this means the MirrorBDSOpaque "s" object has not been initialized yet, and this object is initialized by block_job_create(), but the initialize process is stuck in acquiring the lock. In this situation, IO thread come to bdrv_mirror_top_pwritev(),which means that mirror-top node is already inserted into block graph, but its bs->opaque->job is not initialized. The root cause is that qemu main thread do release/acquire when hold the lock, at the same time, IO thread get the lock after release stage, and the crash occured. Actually, in this situation, job->job.aio_context will not equal to qemu_get_aio_context(), and will be the same as bs->aio_context, thus, no need to release the lock, becasue bdrv_root_attach_child() will not change the context. This patch fix this issue. Fixes: 132ada80 "block: Adjust AioContexts when attaching nodes" Signed-off-by: Michael Qiu <qiudayu@huayun.com> Message-Id: <20210203024059.52683-1-08005325@163.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2021-02-03 05:40:59 +03:00
bool need_context_ops;
bdrv_ref(bs);
blockjob: Fix crash with IOthread when block commit after snapshot Currently, if guest has workloads, IO thread will acquire aio_context lock before do io_submit, it leads to segmentfault when do block commit after snapshot. Just like below: Program received signal SIGSEGV, Segmentation fault. [Switching to Thread 0x7f7c7d91f700 (LWP 99907)] 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437 1437 ../block/mirror.c: No such file or directory. (gdb) p s->job $17 = (MirrorBlockJob *) 0x0 (gdb) p s->stop $18 = false Call trace of IO thread: 0 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437 1 0x00005576d0f7f3ab in bdrv_driver_pwritev at ../block/io.c:1174 2 0x00005576d0f8139d in bdrv_aligned_pwritev at ../block/io.c:1988 3 0x00005576d0f81b65 in bdrv_co_pwritev_part at ../block/io.c:2156 4 0x00005576d0f8e6b7 in blk_do_pwritev_part at ../block/block-backend.c:1260 5 0x00005576d0f8e84d in blk_aio_write_entry at ../block/block-backend.c:1476 ... Switch to qemu main thread: 0 0x00007f903be704ed in __lll_lock_wait at /lib/../lib64/libpthread.so.0 1 0x00007f903be6bde6 in _L_lock_941 at /lib/../lib64/libpthread.so.0 2 0x00007f903be6bcdf in pthread_mutex_lock at /lib/../lib64/libpthread.so.0 3 0x0000564b21456889 in qemu_mutex_lock_impl at ../util/qemu-thread-posix.c:79 4 0x0000564b213af8a5 in block_job_add_bdrv at ../blockjob.c:224 5 0x0000564b213b00ad in block_job_create at ../blockjob.c:440 6 0x0000564b21357c0a in mirror_start_job at ../block/mirror.c:1622 7 0x0000564b2135a9af in commit_active_start at ../block/mirror.c:1867 8 0x0000564b2133d132 in qmp_block_commit at ../blockdev.c:2768 9 0x0000564b2141fef3 in qmp_marshal_block_commit at qapi/qapi-commands-block-core.c:346 10 0x0000564b214503c9 in do_qmp_dispatch_bh at ../qapi/qmp-dispatch.c:110 11 0x0000564b21451996 in aio_bh_poll at ../util/async.c:164 12 0x0000564b2146018e in aio_dispatch at ../util/aio-posix.c:381 13 0x0000564b2145187e in aio_ctx_dispatch at ../util/async.c:306 14 0x00007f9040239049 in g_main_context_dispatch at /lib/../lib64/libglib-2.0.so.0 15 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:232 16 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:255 17 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:531 18 0x0000564b212304e1 in qemu_main_loop at ../softmmu/runstate.c:721 19 0x0000564b20f7975e in main at ../softmmu/main.c:50 In IO thread when do bdrv_mirror_top_pwritev, the job is NULL, and stop field is false, this means the MirrorBDSOpaque "s" object has not been initialized yet, and this object is initialized by block_job_create(), but the initialize process is stuck in acquiring the lock. In this situation, IO thread come to bdrv_mirror_top_pwritev(),which means that mirror-top node is already inserted into block graph, but its bs->opaque->job is not initialized. The root cause is that qemu main thread do release/acquire when hold the lock, at the same time, IO thread get the lock after release stage, and the crash occured. Actually, in this situation, job->job.aio_context will not equal to qemu_get_aio_context(), and will be the same as bs->aio_context, thus, no need to release the lock, becasue bdrv_root_attach_child() will not change the context. This patch fix this issue. Fixes: 132ada80 "block: Adjust AioContexts when attaching nodes" Signed-off-by: Michael Qiu <qiudayu@huayun.com> Message-Id: <20210203024059.52683-1-08005325@163.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2021-02-03 05:40:59 +03:00
need_context_ops = bdrv_get_aio_context(bs) != job->job.aio_context;
if (need_context_ops && job->job.aio_context != qemu_get_aio_context()) {
aio_context_release(job->job.aio_context);
}
c = bdrv_root_attach_child(bs, name, &child_job, 0, perm, shared_perm, job,
errp);
blockjob: Fix crash with IOthread when block commit after snapshot Currently, if guest has workloads, IO thread will acquire aio_context lock before do io_submit, it leads to segmentfault when do block commit after snapshot. Just like below: Program received signal SIGSEGV, Segmentation fault. [Switching to Thread 0x7f7c7d91f700 (LWP 99907)] 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437 1437 ../block/mirror.c: No such file or directory. (gdb) p s->job $17 = (MirrorBlockJob *) 0x0 (gdb) p s->stop $18 = false Call trace of IO thread: 0 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437 1 0x00005576d0f7f3ab in bdrv_driver_pwritev at ../block/io.c:1174 2 0x00005576d0f8139d in bdrv_aligned_pwritev at ../block/io.c:1988 3 0x00005576d0f81b65 in bdrv_co_pwritev_part at ../block/io.c:2156 4 0x00005576d0f8e6b7 in blk_do_pwritev_part at ../block/block-backend.c:1260 5 0x00005576d0f8e84d in blk_aio_write_entry at ../block/block-backend.c:1476 ... Switch to qemu main thread: 0 0x00007f903be704ed in __lll_lock_wait at /lib/../lib64/libpthread.so.0 1 0x00007f903be6bde6 in _L_lock_941 at /lib/../lib64/libpthread.so.0 2 0x00007f903be6bcdf in pthread_mutex_lock at /lib/../lib64/libpthread.so.0 3 0x0000564b21456889 in qemu_mutex_lock_impl at ../util/qemu-thread-posix.c:79 4 0x0000564b213af8a5 in block_job_add_bdrv at ../blockjob.c:224 5 0x0000564b213b00ad in block_job_create at ../blockjob.c:440 6 0x0000564b21357c0a in mirror_start_job at ../block/mirror.c:1622 7 0x0000564b2135a9af in commit_active_start at ../block/mirror.c:1867 8 0x0000564b2133d132 in qmp_block_commit at ../blockdev.c:2768 9 0x0000564b2141fef3 in qmp_marshal_block_commit at qapi/qapi-commands-block-core.c:346 10 0x0000564b214503c9 in do_qmp_dispatch_bh at ../qapi/qmp-dispatch.c:110 11 0x0000564b21451996 in aio_bh_poll at ../util/async.c:164 12 0x0000564b2146018e in aio_dispatch at ../util/aio-posix.c:381 13 0x0000564b2145187e in aio_ctx_dispatch at ../util/async.c:306 14 0x00007f9040239049 in g_main_context_dispatch at /lib/../lib64/libglib-2.0.so.0 15 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:232 16 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:255 17 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:531 18 0x0000564b212304e1 in qemu_main_loop at ../softmmu/runstate.c:721 19 0x0000564b20f7975e in main at ../softmmu/main.c:50 In IO thread when do bdrv_mirror_top_pwritev, the job is NULL, and stop field is false, this means the MirrorBDSOpaque "s" object has not been initialized yet, and this object is initialized by block_job_create(), but the initialize process is stuck in acquiring the lock. In this situation, IO thread come to bdrv_mirror_top_pwritev(),which means that mirror-top node is already inserted into block graph, but its bs->opaque->job is not initialized. The root cause is that qemu main thread do release/acquire when hold the lock, at the same time, IO thread get the lock after release stage, and the crash occured. Actually, in this situation, job->job.aio_context will not equal to qemu_get_aio_context(), and will be the same as bs->aio_context, thus, no need to release the lock, becasue bdrv_root_attach_child() will not change the context. This patch fix this issue. Fixes: 132ada80 "block: Adjust AioContexts when attaching nodes" Signed-off-by: Michael Qiu <qiudayu@huayun.com> Message-Id: <20210203024059.52683-1-08005325@163.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2021-02-03 05:40:59 +03:00
if (need_context_ops && job->job.aio_context != qemu_get_aio_context()) {
aio_context_acquire(job->job.aio_context);
}
if (c == NULL) {
return -EPERM;
}
job->nodes = g_slist_prepend(job->nodes, c);
bdrv_op_block_all(bs, job->blocker);
return 0;
}
static void block_job_on_idle(Notifier *n, void *opaque)
{
aio_wait_kick();
}
bool block_job_is_internal(BlockJob *job)
{
return (job->job.id == NULL);
}
const BlockJobDriver *block_job_driver(BlockJob *job)
{
return container_of(job->job.driver, BlockJobDriver, job_driver);
}
/* Assumes the job_mutex is held */
static bool job_timer_pending(Job *job)
{
return timer_pending(&job->sleep_timer);
}
bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
{
const BlockJobDriver *drv = block_job_driver(job);
int64_t old_speed = job->speed;
if (job_apply_verb(&job->job, JOB_VERB_SET_SPEED, errp) < 0) {
return false;
blockjobs: add block_job_verb permission table Which commands ("verbs") are appropriate for jobs in which state is also somewhat burdensome to keep track of. As of this commit, it looks rather useless, but begins to look more interesting the more states we add to the STM table. A recurring theme is that no verb will apply to an 'undefined' job. Further, it's not presently possible to restrict the "pause" or "resume" verbs any more than they are in this commit because of the asynchronous nature of how jobs enter the PAUSED state; justifications for some seemingly erroneous applications are given below. ===== Verbs ===== Cancel: Any state except undefined. Pause: Any state except undefined; 'created': Requests that the job pauses as it starts. 'running': Normal usage. (PAUSED) 'paused': The job may be paused for internal reasons, but the user may wish to force an indefinite user-pause, so this is allowed. 'ready': Normal usage. (STANDBY) 'standby': Same logic as above. Resume: Any state except undefined; 'created': Will lift a user's pause-on-start request. 'running': Will lift a pause request before it takes effect. 'paused': Normal usage. 'ready': Will lift a pause request before it takes effect. 'standby': Normal usage. Set-speed: Any state except undefined, though ready may not be meaningful. Complete: Only a 'ready' job may accept a complete request. ======= Changes ======= (1) To facilitate "nice" error checking, all five major block-job verb interfaces in blockjob.c now support an errp parameter: - block_job_user_cancel is added as a new interface. - block_job_user_pause gains an errp paramter - block_job_user_resume gains an errp parameter - block_job_set_speed already had an errp parameter. - block_job_complete already had an errp parameter. (2) block-job-pause and block-job-resume will no longer no-op when trying to pause an already paused job, or trying to resume a job that isn't paused. These functions will now report that they did not perform the action requested because it was not possible. iotests have been adjusted to address this new behavior. (3) block-job-complete doesn't worry about checking !block_job_started, because the permission table guards against this. (4) test-bdrv-drain's job implementation needs to announce that it is 'ready' now, in order to be completed. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2018-03-10 11:27:32 +03:00
}
if (speed < 0) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "speed",
"a non-negative value");
return false;
}
ratelimit_set_speed(&job->limit, speed, BLOCK_JOB_SLICE_TIME);
job->speed = speed;
if (drv->set_speed) {
drv->set_speed(job, speed);
}
if (speed && speed <= old_speed) {
return true;
}
/* kick only if a timer is pending */
job_enter_cond(&job->job, job_timer_pending);
return true;
}
int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n)
{
return ratelimit_calculate_delay(&job->limit, n);
}
BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
{
BlockJobInfo *info;
uint64_t progress_current, progress_total;
if (block_job_is_internal(job)) {
error_setg(errp, "Cannot query QEMU internal jobs");
return NULL;
}
progress_get_snapshot(&job->job.progress, &progress_current,
&progress_total);
info = g_new0(BlockJobInfo, 1);
info->type = g_strdup(job_type_str(&job->job));
info->device = g_strdup(job->job.id);
info->busy = qatomic_read(&job->job.busy);
info->paused = job->job.pause_count > 0;
info->offset = progress_current;
info->len = progress_total;
info->speed = job->speed;
info->io_status = job->iostatus;
info->ready = job_is_ready(&job->job),
info->status = job->job.status;
info->auto_finalize = job->job.auto_finalize;
info->auto_dismiss = job->job.auto_dismiss;
if (job->job.ret) {
info->has_error = true;
info->error = job->job.err ?
g_strdup(error_get_pretty(job->job.err)) :
g_strdup(strerror(-job->job.ret));
}
return info;
}
static void block_job_iostatus_set_err(BlockJob *job, int error)
{
if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
job->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
BLOCK_DEVICE_IO_STATUS_FAILED;
}
}
static void block_job_event_cancelled(Notifier *n, void *opaque)
{
BlockJob *job = opaque;
uint64_t progress_current, progress_total;
if (block_job_is_internal(job)) {
return;
}
progress_get_snapshot(&job->job.progress, &progress_current,
&progress_total);
qapi_event_send_block_job_cancelled(job_type(&job->job),
job->job.id,
progress_total,
progress_current,
job->speed);
}
static void block_job_event_completed(Notifier *n, void *opaque)
{
BlockJob *job = opaque;
const char *msg = NULL;
uint64_t progress_current, progress_total;
if (block_job_is_internal(job)) {
return;
}
if (job->job.ret < 0) {
msg = error_get_pretty(job->job.err);
}
progress_get_snapshot(&job->job.progress, &progress_current,
&progress_total);
qapi_event_send_block_job_completed(job_type(&job->job),
job->job.id,
progress_total,
progress_current,
job->speed,
!!msg,
msg);
}
static void block_job_event_pending(Notifier *n, void *opaque)
{
BlockJob *job = opaque;
if (block_job_is_internal(job)) {
return;
}
qapi_event_send_block_job_pending(job_type(&job->job),
job->job.id);
}
static void block_job_event_ready(Notifier *n, void *opaque)
{
BlockJob *job = opaque;
uint64_t progress_current, progress_total;
if (block_job_is_internal(job)) {
return;
}
progress_get_snapshot(&job->job.progress, &progress_current,
&progress_total);
qapi_event_send_block_job_ready(job_type(&job->job),
job->job.id,
progress_total,
progress_current,
job->speed);
}
/*
* API for block job drivers and the block layer. These functions are
* declared in blockjob_int.h.
*/
void *block_job_create(const char *job_id, const BlockJobDriver *driver,
JobTxn *txn, BlockDriverState *bs, uint64_t perm,
uint64_t shared_perm, int64_t speed, int flags,
BlockCompletionFunc *cb, void *opaque, Error **errp)
{
BlockBackend *blk;
BlockJob *job;
if (job_id == NULL && !(flags & JOB_INTERNAL)) {
job_id = bdrv_get_device_name(bs);
}
blk = blk_new_with_bs(bs, perm, shared_perm, errp);
if (!blk) {
return NULL;
}
job = job_create(job_id, &driver->job_driver, txn, blk_get_aio_context(blk),
flags, cb, opaque, errp);
if (job == NULL) {
blk_unref(blk);
return NULL;
}
assert(is_block_job(&job->job));
assert(job->job.driver->free == &block_job_free);
assert(job->job.driver->user_resume == &block_job_user_resume);
ratelimit_init(&job->limit);
job->blk = blk;
job->finalize_cancelled_notifier.notify = block_job_event_cancelled;
job->finalize_completed_notifier.notify = block_job_event_completed;
job->pending_notifier.notify = block_job_event_pending;
job->ready_notifier.notify = block_job_event_ready;
job->idle_notifier.notify = block_job_on_idle;
notifier_list_add(&job->job.on_finalize_cancelled,
&job->finalize_cancelled_notifier);
notifier_list_add(&job->job.on_finalize_completed,
&job->finalize_completed_notifier);
notifier_list_add(&job->job.on_pending, &job->pending_notifier);
notifier_list_add(&job->job.on_ready, &job->ready_notifier);
notifier_list_add(&job->job.on_idle, &job->idle_notifier);
error_setg(&job->blocker, "block device is in use by block job: %s",
job_type_str(&job->job));
block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort);
bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
/* Disable request queuing in the BlockBackend to avoid deadlocks on drain:
* The job reports that it's busy until it reaches a pause point. */
blk_set_disable_request_queuing(blk, true);
blk_set_allow_aio_context_change(blk, true);
if (!block_job_set_speed(job, speed, errp)) {
job_early_fail(&job->job);
return NULL;
}
return job;
}
void block_job_iostatus_reset(BlockJob *job)
{
if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
return;
}
assert(job->job.user_paused && job->job.pause_count > 0);
job->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
}
void block_job_user_resume(Job *job)
{
BlockJob *bjob = container_of(job, BlockJob, job);
block_job_iostatus_reset(bjob);
}
BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err,
int is_read, int error)
{
BlockErrorAction action;
switch (on_err) {
case BLOCKDEV_ON_ERROR_ENOSPC:
case BLOCKDEV_ON_ERROR_AUTO:
action = (error == ENOSPC) ?
BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_STOP:
action = BLOCK_ERROR_ACTION_STOP;
break;
case BLOCKDEV_ON_ERROR_REPORT:
action = BLOCK_ERROR_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_IGNORE:
action = BLOCK_ERROR_ACTION_IGNORE;
break;
default:
abort();
}
if (!block_job_is_internal(job)) {
qapi_event_send_block_job_error(job->job.id,
is_read ? IO_OPERATION_TYPE_READ :
IO_OPERATION_TYPE_WRITE,
action);
}
if (action == BLOCK_ERROR_ACTION_STOP) {
if (!job->job.user_paused) {
job_pause(&job->job);
/* make the pause user visible, which will be resumed from QMP. */
job->job.user_paused = true;
}
block_job_iostatus_set_err(job, error);
}
return action;
}