job.c: enable job lock/unlock and remove Aiocontext locks

Change the job_{lock/unlock} and macros to use job_mutex.

Now that they are not nop anymore, remove the aiocontext
to avoid deadlocks.

Therefore:
- when possible, remove completely the aiocontext lock/unlock pair
- if it is used by some other function too, reduce the locking
  section as much as possible, leaving the job API outside.
- change AIO_WAIT_WHILE in AIO_WAIT_WHILE_UNLOCKED, since we
  are not using the aiocontext lock anymore

The only functions that still need the aiocontext lock are:
- the JobDriver callbacks, already documented in job.h
- job_cancel_sync() in replication.c is called with aio_context_lock
  taken, but now job is using AIO_WAIT_WHILE_UNLOCKED so we need to
  release the lock.

Reduce the locking section to only cover the callback invocation
and document the functions that take the AioContext lock,
to avoid taking it twice.

Also remove real_job_{lock/unlock}, as they are replaced by the
public functions.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20220926093214.506243-19-eesposit@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

1 files changed, 9 insertions, 8 deletions

diff --git a/include/qemu/job.h b/include/qemu/job.h
index b943d90..a54fb83 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -88,7 +88,7 @@ typedef struct Job {
     AioContext *aio_context;
 
 
-    /** Protected by AioContext lock */
+    /** Protected by job_mutex */
 
     /** Reference count of the block job */
     int refcnt;
@@ -111,7 +111,7 @@ typedef struct Job {
     /**
      * Set to false by the job while the coroutine has yielded and may be
      * re-entered by job_enter(). There may still be I/O or event loop activity
-     * pending. Accessed under block_job_mutex (in blockjob.c).
+     * pending. Accessed under job_mutex.
      *
      * When the job is deferred to the main loop, busy is true as long as the
      * bottom half is still pending.
@@ -346,9 +346,9 @@ typedef enum JobCreateFlags {
 
 extern QemuMutex job_mutex;
 
-#define JOB_LOCK_GUARD() /* QEMU_LOCK_GUARD(&job_mutex) */
+#define JOB_LOCK_GUARD() QEMU_LOCK_GUARD(&job_mutex)
 
-#define WITH_JOB_LOCK_GUARD() /* WITH_QEMU_LOCK_GUARD(&job_mutex) */
+#define WITH_JOB_LOCK_GUARD() WITH_QEMU_LOCK_GUARD(&job_mutex)
 
 /**
  * job_lock:
@@ -422,6 +422,8 @@ void job_ref_locked(Job *job);
 /**
  * Release a reference that was previously acquired with job_ref() or
  * job_create(). If it's the last reference to the object, it will be freed.
+ *
+ * Takes AioContext lock internally to invoke a job->driver callback.
  */
 void job_unref(Job *job);
 
@@ -696,7 +698,7 @@ void job_user_cancel_locked(Job *job, bool force, Error **errp);
  * 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.
+ * Called with job_lock *not* held.
  */
 int job_cancel_sync(Job *job, bool force);
 
@@ -721,8 +723,7 @@ void job_cancel_sync_all(void);
  * function).
  *
  * Returns the return value from the job.
- *
- * Callers must hold the AioContext lock of job->aio_context.
+ * Called with job_lock *not* held.
  */
 int job_complete_sync(Job *job, Error **errp);
 
@@ -758,7 +759,7 @@ void job_dismiss_locked(Job **job, Error **errp);
  * Returns 0 if the job is successfully completed, -ECANCELED if the job was
  * cancelled before completing, and -errno in other error cases.
  *
- * Callers must hold the AioContext lock of job->aio_context.
+ * Called with job_lock *not* held.
  */
 int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp),
                     Error **errp);