*/
#include "qemu/osdep.h"
-#include "qemu-common.h"
#include "qapi/error.h"
#include "qemu/job.h"
#include "qemu/id.h"
#include "qemu/main-loop.h"
-#include "trace-root.h"
+#include "block/aio-wait.h"
+#include "trace/trace-root.h"
+#include "qapi/qapi-events-job.h"
static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs);
[JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
[JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
[JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0},
- [JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0},
+ [JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0},
[JOB_VERB_FINALIZE] = {0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0},
[JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0},
};
}
}
-static int job_txn_apply(JobTxn *txn, int fn(Job *), bool lock)
+static int job_txn_apply(Job *job, int fn(Job *))
{
- AioContext *ctx;
- Job *job, *next;
+ AioContext *inner_ctx;
+ Job *other_job, *next;
+ JobTxn *txn = job->txn;
int rc = 0;
- QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
- if (lock) {
- ctx = job->aio_context;
- aio_context_acquire(ctx);
- }
- rc = fn(job);
- if (lock) {
- aio_context_release(ctx);
- }
+ /*
+ * Similar to job_completed_txn_abort, we take each job's lock before
+ * applying fn, but since we assume that outer_ctx is held by the caller,
+ * we need to release it here to avoid holding the lock twice - which would
+ * break AIO_WAIT_WHILE from within fn.
+ */
+ job_ref(job);
+ aio_context_release(job->aio_context);
+
+ QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) {
+ inner_ctx = other_job->aio_context;
+ aio_context_acquire(inner_ctx);
+ rc = fn(other_job);
+ aio_context_release(inner_ctx);
if (rc) {
break;
}
}
+
+ /*
+ * Note that job->aio_context might have been changed by calling fn, so we
+ * can't use a local variable to cache it.
+ */
+ aio_context_acquire(job->aio_context);
+ job_unref(job);
return rc;
}
+bool job_is_internal(Job *job)
+{
+ return (job->id == NULL);
+}
+
static void job_state_transition(Job *job, JobStatus s1)
{
JobStatus s0 = job->status;
- assert(s1 >= 0 && s1 <= JOB_STATUS__MAX);
+ assert(s1 >= 0 && s1 < JOB_STATUS__MAX);
trace_job_state_transition(job, job->ret,
JobSTT[s0][s1] ? "allowed" : "disallowed",
JobStatus_str(s0), JobStatus_str(s1));
assert(JobSTT[s0][s1]);
job->status = s1;
+
+ if (!job_is_internal(job) && s1 != s0) {
+ qapi_event_send_job_status_change(job->id, job->status);
+ }
}
int job_apply_verb(Job *job, JobVerb verb, Error **errp)
{
JobStatus s0 = job->status;
- assert(verb >= 0 && verb <= JOB_VERB__MAX);
+ assert(verb >= 0 && verb < JOB_VERB__MAX);
trace_job_apply_verb(job, JobStatus_str(s0), JobVerb_str(verb),
JobVerbTable[verb][s0] ? "allowed" : "prohibited");
if (JobVerbTable[verb][s0]) {
}
bool job_is_cancelled(Job *job)
+{
+ /* force_cancel may be true only if cancelled is true, too */
+ assert(job->cancelled || !job->force_cancel);
+ return job->force_cancel;
+}
+
+bool job_cancel_requested(Job *job)
{
return job->cancelled;
}
job->cb = cb;
job->opaque = opaque;
+ progress_init(&job->progress);
+
notifier_list_init(&job->on_finalize_cancelled);
notifier_list_init(&job->on_finalize_completed);
notifier_list_init(&job->on_pending);
notifier_list_init(&job->on_ready);
+ notifier_list_init(&job->on_idle);
job_state_transition(job, JOB_STATUS_CREATED);
aio_timer_init(qemu_get_aio_context(), &job->sleep_timer,
void job_unref(Job *job)
{
+ GLOBAL_STATE_CODE();
+
if (--job->refcnt == 0) {
assert(job->status == JOB_STATUS_NULL);
assert(!timer_pending(&job->sleep_timer));
QLIST_REMOVE(job, job_list);
+ progress_destroy(&job->progress);
+ error_free(job->err);
g_free(job->id);
g_free(job);
}
}
+void job_progress_update(Job *job, uint64_t done)
+{
+ progress_work_done(&job->progress, done);
+}
+
+void job_progress_set_remaining(Job *job, uint64_t remaining)
+{
+ progress_set_remaining(&job->progress, remaining);
+}
+
+void job_progress_increase_remaining(Job *job, uint64_t delta)
+{
+ progress_increase_remaining(&job->progress, delta);
+}
+
void job_event_cancelled(Job *job)
{
notifier_list_notify(&job->on_finalize_cancelled, job);
notifier_list_notify(&job->on_ready, job);
}
+static void job_event_idle(Job *job)
+{
+ notifier_list_notify(&job->on_idle, job);
+}
+
void job_enter_cond(Job *job, bool(*fn)(Job *job))
{
if (!job_started(job)) {
timer_del(&job->sleep_timer);
job->busy = true;
job_unlock();
- aio_co_wake(job->co);
+ aio_co_enter(job->aio_context, job->co);
}
void job_enter(Job *job)
timer_mod(&job->sleep_timer, ns);
}
job->busy = false;
+ job_event_idle(job);
job_unlock();
qemu_coroutine_yield();
job_pause_point(job);
}
-void job_drain(Job *job)
-{
- /* If job is !busy this kicks it into the next pause point. */
- job_enter(job);
-
- if (job->driver->drain) {
- job->driver->drain(job);
- }
-}
-
-
-/**
- * All jobs must allow a pause point before entering their job proper. This
- * ensures that jobs can be paused prior to being started, then resumed later.
- */
-static void coroutine_fn job_co_entry(void *opaque)
-{
- Job *job = opaque;
-
- assert(job && job->driver && job->driver->start);
- job_pause_point(job);
- job->driver->start(job);
-}
-
-
-void job_start(Job *job)
-{
- assert(job && !job_started(job) && job->paused &&
- job->driver && job->driver->start);
- job->co = qemu_coroutine_create(job_co_entry, job);
- job->pause_count--;
- job->busy = true;
- job->paused = false;
- job_state_transition(job, JOB_STATUS_RUNNING);
- aio_co_enter(job->aio_context, job->co);
-}
-
/* Assumes the block_job_mutex is held */
static bool job_timer_not_pending(Job *job)
{
void job_pause(Job *job)
{
job->pause_count++;
+ if (!job->paused) {
+ job_enter(job);
+ }
}
void job_resume(Job *job)
void job_user_resume(Job *job, Error **errp)
{
assert(job);
+ GLOBAL_STATE_CODE();
if (!job->user_paused || job->pause_count <= 0) {
error_setg(errp, "Can't resume a job that was not paused");
return;
job->ret = -ECANCELED;
}
if (job->ret) {
+ if (!job->err) {
+ error_setg(&job->err, "%s", strerror(-job->ret));
+ }
job_state_transition(job, JOB_STATUS_ABORTING);
}
}
static void job_commit(Job *job)
{
assert(!job->ret);
+ GLOBAL_STATE_CODE();
if (job->driver->commit) {
job->driver->commit(job);
}
static void job_abort(Job *job)
{
assert(job->ret);
+ GLOBAL_STATE_CODE();
if (job->driver->abort) {
job->driver->abort(job);
}
static void job_clean(Job *job)
{
+ GLOBAL_STATE_CODE();
if (job->driver->clean) {
job->driver->clean(job);
}
static void job_cancel_async(Job *job, bool force)
{
+ GLOBAL_STATE_CODE();
+ if (job->driver->cancel) {
+ force = job->driver->cancel(job, force);
+ } else {
+ /* No .cancel() means the job will behave as if force-cancelled */
+ force = true;
+ }
+
if (job->user_paused) {
/* Do not call job_enter here, the caller will handle it. */
- job->user_paused = false;
if (job->driver->user_resume) {
job->driver->user_resume(job);
}
+ job->user_paused = false;
assert(job->pause_count > 0);
job->pause_count--;
}
- job->cancelled = true;
- /* To prevent 'force == false' overriding a previous 'force == true' */
- job->force_cancel |= force;
+
+ /*
+ * Ignore soft cancel requests after the job is already done
+ * (We will still invoke job->driver->cancel() above, but if the
+ * job driver supports soft cancelling and the job is done, that
+ * should be a no-op, too. We still call it so it can override
+ * @force.)
+ */
+ if (force || !job->deferred_to_main_loop) {
+ job->cancelled = true;
+ /* To prevent 'force == false' overriding a previous 'force == true' */
+ job->force_cancel |= force;
+ }
}
static void job_completed_txn_abort(Job *job)
txn->aborting = true;
job_txn_ref(txn);
- /* We are the first failed job. Cancel other jobs. */
- QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
- ctx = other_job->aio_context;
- aio_context_acquire(ctx);
- }
+ /*
+ * We can only hold the single job's AioContext lock while calling
+ * job_finalize_single() because the finalization callbacks can involve
+ * calls of AIO_WAIT_WHILE(), which could deadlock otherwise.
+ * Note that the job's AioContext may change when it is finalized.
+ */
+ job_ref(job);
+ aio_context_release(job->aio_context);
/* Other jobs are effectively cancelled by us, set the status for
* them; this job, however, may or may not be cancelled, depending
* on the caller, so leave it. */
QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
if (other_job != job) {
- job_cancel_async(other_job, false);
+ ctx = other_job->aio_context;
+ aio_context_acquire(ctx);
+ /*
+ * This is a transaction: If one job failed, no result will matter.
+ * Therefore, pass force=true to terminate all other jobs as quickly
+ * as possible.
+ */
+ job_cancel_async(other_job, true);
+ aio_context_release(ctx);
}
}
while (!QLIST_EMPTY(&txn->jobs)) {
other_job = QLIST_FIRST(&txn->jobs);
+ /*
+ * The job's AioContext may change, so store it in @ctx so we
+ * release the same context that we have acquired before.
+ */
ctx = other_job->aio_context;
+ aio_context_acquire(ctx);
if (!job_is_completed(other_job)) {
- assert(job_is_cancelled(other_job));
+ assert(job_cancel_requested(other_job));
job_finish_sync(other_job, NULL, NULL);
}
job_finalize_single(other_job);
aio_context_release(ctx);
}
+ /*
+ * Use job_ref()/job_unref() so we can read the AioContext here
+ * even if the job went away during job_finalize_single().
+ */
+ aio_context_acquire(job->aio_context);
+ job_unref(job);
+
job_txn_unref(txn);
}
static int job_prepare(Job *job)
{
+ GLOBAL_STATE_CODE();
if (job->ret == 0 && job->driver->prepare) {
job->ret = job->driver->prepare(job);
+ job_update_rc(job);
}
return job->ret;
}
assert(job && job->txn);
/* prepare the transaction to complete */
- rc = job_txn_apply(job->txn, job_prepare, true);
+ rc = job_txn_apply(job, job_prepare);
if (rc) {
job_completed_txn_abort(job);
} else {
- job_txn_apply(job->txn, job_finalize_single, true);
+ job_txn_apply(job, job_finalize_single);
}
}
assert(other_job->ret == 0);
}
- job_txn_apply(txn, job_transition_to_pending, false);
+ job_txn_apply(job, job_transition_to_pending);
/* If no jobs need manual finalization, automatically do so */
- if (job_txn_apply(txn, job_needs_finalize, false) == 0) {
+ if (job_txn_apply(job, job_needs_finalize) == 0) {
job_do_finalize(job);
}
}
-void job_completed(Job *job, int ret)
+static void job_completed(Job *job)
{
assert(job && job->txn && !job_is_completed(job));
- job->ret = ret;
+
job_update_rc(job);
- trace_job_completed(job, ret, job->ret);
+ trace_job_completed(job, job->ret);
if (job->ret) {
job_completed_txn_abort(job);
} else {
}
}
+/** Useful only as a type shim for aio_bh_schedule_oneshot. */
+static void job_exit(void *opaque)
+{
+ Job *job = (Job *)opaque;
+ AioContext *ctx;
+
+ job_ref(job);
+ aio_context_acquire(job->aio_context);
+
+ /* This is a lie, we're not quiescent, but still doing the completion
+ * callbacks. However, completion callbacks tend to involve operations that
+ * drain block nodes, and if .drained_poll still returned true, we would
+ * deadlock. */
+ job->busy = false;
+ job_event_idle(job);
+
+ job_completed(job);
+
+ /*
+ * Note that calling job_completed can move the job to a different
+ * aio_context, so we cannot cache from above. job_txn_apply takes care of
+ * acquiring the new lock, and we ref/unref to avoid job_completed freeing
+ * the job underneath us.
+ */
+ ctx = job->aio_context;
+ job_unref(job);
+ aio_context_release(ctx);
+}
+
+/**
+ * All jobs must allow a pause point before entering their job proper. This
+ * ensures that jobs can be paused prior to being started, then resumed later.
+ */
+static void coroutine_fn job_co_entry(void *opaque)
+{
+ Job *job = opaque;
+
+ assert(job && job->driver && job->driver->run);
+ assert(job->aio_context == qemu_get_current_aio_context());
+ job_pause_point(job);
+ job->ret = job->driver->run(job, &job->err);
+ job->deferred_to_main_loop = true;
+ job->busy = true;
+ aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);
+}
+
+void job_start(Job *job)
+{
+ assert(job && !job_started(job) && job->paused &&
+ job->driver && job->driver->run);
+ job->co = qemu_coroutine_create(job_co_entry, job);
+ job->pause_count--;
+ job->busy = true;
+ job->paused = false;
+ job_state_transition(job, JOB_STATUS_RUNNING);
+ aio_co_enter(job->aio_context, job->co);
+}
+
void job_cancel(Job *job, bool force)
{
if (job->status == JOB_STATUS_CONCLUDED) {
}
job_cancel_async(job, force);
if (!job_started(job)) {
- job_completed(job, -ECANCELED);
+ job_completed(job);
} else if (job->deferred_to_main_loop) {
- job_completed_txn_abort(job);
+ /*
+ * job_cancel_async() ignores soft-cancel requests for jobs
+ * that are already done (i.e. deferred to the main loop). We
+ * have to check again whether the job is really cancelled.
+ * (job_cancel_requested() and job_is_cancelled() are equivalent
+ * here, because job_cancel_async() will make soft-cancel
+ * requests no-ops when deferred_to_main_loop is true. We
+ * choose to call job_is_cancelled() to show that we invoke
+ * job_completed_txn_abort() only for force-cancelled jobs.)
+ */
+ if (job_is_cancelled(job)) {
+ job_completed_txn_abort(job);
+ }
} else {
job_enter(job);
}
job_cancel(job, false);
}
-int job_cancel_sync(Job *job)
+/**
+ * Same as job_cancel_err(), but force-cancel.
+ */
+static void job_force_cancel_err(Job *job, Error **errp)
+{
+ job_cancel(job, true);
+}
+
+int job_cancel_sync(Job *job, bool force)
{
- return job_finish_sync(job, &job_cancel_err, NULL);
+ if (force) {
+ return job_finish_sync(job, &job_force_cancel_err, NULL);
+ } else {
+ return job_finish_sync(job, &job_cancel_err, NULL);
+ }
}
void job_cancel_sync_all(void)
while ((job = job_next(NULL))) {
aio_context = job->aio_context;
aio_context_acquire(aio_context);
- job_cancel_sync(job);
+ job_cancel_sync(job, true);
aio_context_release(aio_context);
}
}
{
/* Should not be reachable via external interface for internal jobs */
assert(job->id);
+ GLOBAL_STATE_CODE();
if (job_apply_verb(job, JOB_VERB_COMPLETE, errp)) {
return;
}
- if (job->pause_count || job_is_cancelled(job) || !job->driver->complete) {
+ if (job_cancel_requested(job) || !job->driver->complete) {
error_setg(errp, "The active block job '%s' cannot be completed",
job->id);
return;
job->driver->complete(job, errp);
}
-
-typedef struct {
- Job *job;
- JobDeferToMainLoopFn *fn;
- void *opaque;
-} JobDeferToMainLoopData;
-
-static void job_defer_to_main_loop_bh(void *opaque)
-{
- JobDeferToMainLoopData *data = opaque;
- Job *job = data->job;
- AioContext *aio_context = job->aio_context;
-
- aio_context_acquire(aio_context);
- data->fn(data->job, data->opaque);
- aio_context_release(aio_context);
-
- g_free(data);
-}
-
-void job_defer_to_main_loop(Job *job, JobDeferToMainLoopFn *fn, void *opaque)
-{
- JobDeferToMainLoopData *data = g_malloc(sizeof(*data));
- data->job = job;
- data->fn = fn;
- data->opaque = opaque;
- job->deferred_to_main_loop = true;
-
- aio_bh_schedule_oneshot(qemu_get_aio_context(),
- job_defer_to_main_loop_bh, data);
-}
-
int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
{
Error *local_err = NULL;
job_unref(job);
return -EBUSY;
}
- /* job_drain calls job_enter, and it should be enough to induce progress
- * until the job completes or moves to the main thread. */
- while (!job->deferred_to_main_loop && !job_is_completed(job)) {
- job_drain(job);
- }
- while (!job_is_completed(job)) {
- aio_poll(qemu_get_aio_context(), true);
- }
+
+ AIO_WAIT_WHILE(job->aio_context,
+ (job_enter(job), !job_is_completed(job)));
+
ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret;
job_unref(job);
return ret;
projects / mirror_qemu.git / blobdiff