blockjob: Fix hang in block_job_finish_sync

With a mirror job running on a virtio-blk dataplane disk, sending "q" to
HMP will cause a dead loop in block_job_finish_sync.

This is because the aio_poll() only processes the AIO context of bs
which has no more work to do, while the main loop BH that is scheduled
for setting the job->completed flag is never processed.

Fix this by adding a flag in BlockJob structure, to track which context
to poll for the block job to make progress. Its value is set to true
when block_job_coroutine_complete() is called, and is checked in
block_job_finish_sync to determine which context to poll.

Suggested-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
Message-id: 1454379144-29807-1-git-send-email-famz@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 5 insertions, 1 deletions

diff --git a/blockjob.c b/blockjob.c
index a402181835..9fc37ca965 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -296,7 +296,9 @@ static int block_job_finish_sync(BlockJob *job,
         return -EBUSY;
     }
     while (!job->completed) {
-        aio_poll(bdrv_get_aio_context(bs), true);
+        aio_poll(job->deferred_to_main_loop ? qemu_get_aio_context() :
+                                              bdrv_get_aio_context(bs),
+                 true);
     }
     ret = (job->cancelled && job->ret == 0) ? -ECANCELED : job->ret;
     block_job_unref(job);
@@ -470,6 +472,7 @@ static void block_job_defer_to_main_loop_bh(void *opaque)
     aio_context = bdrv_get_aio_context(data->job->bs);
     aio_context_acquire(aio_context);
 
+    data->job->deferred_to_main_loop = false;
     data->fn(data->job, data->opaque);
 
     aio_context_release(aio_context);
@@ -489,6 +492,7 @@ void block_job_defer_to_main_loop(BlockJob *job,
     data->aio_context = bdrv_get_aio_context(job->bs);
     data->fn = fn;
     data->opaque = opaque;
+    job->deferred_to_main_loop = true;
 
     qemu_bh_schedule(data->bh);
 }