block: Really pause block jobs on drain

We already requested that block jobs be paused in .bdrv_drained_begin,
but no guarantee was made that the job was actually inactive at the
point where bdrv_drained_begin() returned.

This introduces a new callback BdrvChildRole.bdrv_drained_poll() and
uses it to make bdrv_drain_poll() consider block jobs using the node to
be drained.

For the test case to work as expected, we have to switch from
block_job_sleep_ns() to qemu_co_sleep_ns() so that the test job is even
considered active and must be waited for when draining the node.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>

3 files changed, 23 insertions, 0 deletions

diff --git a/include/block/block.h b/include/block/block.h
index e677080..cebbb39 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -568,6 +568,14 @@ void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore);
 void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore);
 
 /**
+ * bdrv_drain_poll:
+ *
+ * Poll for pending requests in @bs and its parents (except for
+ * @ignore_parent). This is part of bdrv_drained_begin.
+ */
+bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent);
+
+/**
  * bdrv_drained_begin:
  *
  * Begin a quiesced section for exclusive access to the BDS, by disabling
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 327e478..1b811db 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -605,6 +605,13 @@ struct BdrvChildRole {
     void (*drained_begin)(BdrvChild *child);
     void (*drained_end)(BdrvChild *child);
 
+    /*
+     * Returns whether the parent has pending requests for the child. This
+     * callback is polled after .drained_begin() has been called until all
+     * activity on the child has stopped.
+     */
+    bool (*drained_poll)(BdrvChild *child);
+
     /* Notifies the parent that the child has been activated/inactivated (e.g.
      * when migration is completing) and it can start/stop requesting
      * permissions and doing I/O on it. */
diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h
index 5cd50c6..e4a318d 100644
--- a/include/block/blockjob_int.h
+++ b/include/block/blockjob_int.h
@@ -39,6 +39,14 @@ struct BlockJobDriver {
     JobDriver job_driver;
 
     /*
+     * Returns whether the job has pending requests for the child or will
+     * submit new requests before the next pause point. This callback is polled
+     * in the context of draining a job node after requesting that the job be
+     * paused, until all activity on the child has stopped.
+     */
+    bool (*drained_poll)(BlockJob *job);
+
+    /*
      * If the callback is not NULL, it will be invoked before the job is
      * resumed in a new AioContext.  This is the place to move any resources
      * besides job->blk to the new AioContext.