job: @force parameter for job_cancel_sync()

Callers should be able to specify whether they want job_cancel_sync() to
force-cancel the job or not.

In fact, almost all invocations do not care about consistency of the
result and just want the job to terminate as soon as possible, so they
should pass force=true.  The replication block driver is the exception,
specifically the active commit job it runs.

As for job_cancel_sync_all(), all callers want it to force-cancel all
jobs, because that is the point of it: To cancel all remaining jobs as
quickly as possible (generally on process termination).  So make it
invoke job_cancel_sync() with force=true.

This changes some iotest outputs, because quitting qemu while a mirror
job is active will now lead to it being cancelled instead of completed,
which is what we want.  (Cancelling a READY mirror job with force=false
may take an indefinite amount of time, which we do not want when
quitting.  If users want consistent results, they must have all jobs be
done before they quit qemu.)

Buglink: https://gitlab.com/qemu-project/qemu/-/issues/462
Signed-off-by: Hanna Reitz <[email protected]>
Reviewed-by: Eric Blake <[email protected]>
Reviewed-by: Vladimir Sementsov-Ogievskiy <[email protected]>
Message-Id: <[email protected]>
Signed-off-by: Vladimir Sementsov-Ogievskiy <[email protected]>

block/replication.c

@@ -149,7 +149,7 @@ static void replication_close(BlockDriverState *bs)
     if (s->stage == BLOCK_REPLICATION_FAILOVER) {
         commit_job = &s->commit_job->job;
         assert(commit_job->aio_context == qemu_get_current_aio_context());
-        job_cancel_sync(commit_job);
+        job_cancel_sync(commit_job, false);
     }
 
     if (s->mode == REPLICATION_MODE_SECONDARY) {
@@ -726,7 +726,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
          * disk, secondary disk in backup_job_completed().
          */
         if (s->backup_job) {
-            job_cancel_sync(&s->backup_job->job);
+            job_cancel_sync(&s->backup_job->job, true);
         }
 
         if (!failover) {

blockdev.c

@@ -1847,7 +1847,7 @@ static void drive_backup_abort(BlkActionState *common)
         aio_context = bdrv_get_aio_context(state->bs);
         aio_context_acquire(aio_context);
 
-        job_cancel_sync(&state->job->job);
+        job_cancel_sync(&state->job->job, true);
 
         aio_context_release(aio_context);
     }
@@ -1948,7 +1948,7 @@ static void blockdev_backup_abort(BlkActionState *common)
         aio_context = bdrv_get_aio_context(state->bs);
         aio_context_acquire(aio_context);
 
-        job_cancel_sync(&state->job->job);
+        job_cancel_sync(&state->job->job, true);
 
         aio_context_release(aio_context);
     }

include/qemu/job.h

@@ -506,18 +506,18 @@ void job_user_cancel(Job *job, bool force, Error **errp);
 
 /**
  * Synchronously cancel the @job.  The completion callback is called
- * before the function returns.  The job may actually complete
- * instead of canceling itself; the circumstances under which this
- * happens depend on the kind of job that is active.
+ * before the function returns.  If @force is false, the job may
+ * actually complete instead of canceling itself; the circumstances
+ * under which this happens depend on the kind of job that is active.
  *
  * Returns the return value from the job if the job actually completed
  * during the call, or -ECANCELED if it was canceled.
  *
  * Callers must hold the AioContext lock of job->aio_context.
  */
-int job_cancel_sync(Job *job);
+int job_cancel_sync(Job *job, bool force);
 
-/** Synchronously cancels all jobs using job_cancel_sync(). */
+/** Synchronously force-cancels all jobs using job_cancel_sync(). */
 void job_cancel_sync_all(void);
 
 /**

job.c

@@ -981,9 +981,21 @@ static void job_cancel_err(Job *job, Error **errp)
     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)
 {
-    return job_finish_sync(job, &job_cancel_err, NULL);
+    job_cancel(job, true);
+}
+
+int job_cancel_sync(Job *job, bool force)
+{
+    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)
@@ -994,7 +1006,7 @@ 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);
     }
 }

tests/qemu-iotests/tests/qsd-jobs.out

@@ -8,7 +8,7 @@ QMP_VERSION
 {"return": {}}
 {"return": {}}
 {"return": {}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
 
 === Streaming can't get permission on base node ===
 

tests/unit/test-blockjob.c

@@ -230,7 +230,7 @@ static void cancel_common(CancelJob *s)
     ctx = job->job.aio_context;
     aio_context_acquire(ctx);
 
-    job_cancel_sync(&job->job);
+    job_cancel_sync(&job->job, true);
     if (sts != JOB_STATUS_CREATED && sts != JOB_STATUS_CONCLUDED) {
         Job *dummy = &job->job;
         job_dismiss(&dummy, &error_abort);