blockjob: reimplement block_job_sleep_ns to allow cancellation

This reverts the effects of commit 4afeffc857 ("blockjob: do not allow
coroutine double entry or entry-after-completion", 2017-11-21)

This fixed the symptom of a bug rather than the root cause. Canceling the
wait on a sleeping blockjob coroutine is generally fine, we just need to
make it work correctly across AioContexts.  To do so, use a QEMUTimer
that calls block_job_enter.  Use a mutex to ensure that block_job_enter
synchronizes correctly with block_job_sleep_ns.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-By: Jeff Cody <jcody@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

2 files changed, 9 insertions, 3 deletions

diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 67c0968fa5..00403d9482 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -77,7 +77,7 @@ typedef struct BlockJob {
     /**
      * Set to false by the job while the coroutine has yielded and may be
      * re-entered by block_job_enter().  There may still be I/O or event loop
-     * activity pending.
+     * activity pending.  Accessed under block_job_mutex (in blockjob.c).
      */
     bool busy;
 
@@ -135,6 +135,12 @@ typedef struct BlockJob {
      */
     int ret;
 
+    /**
+     * Timer that is used by @block_job_sleep_ns. Accessed under
+     * block_job_mutex (in blockjob.c).
+     */
+    QEMUTimer sleep_timer;
+
     /** Non-NULL if this job is part of a transaction */
     BlockJobTxn *txn;
     QLIST_ENTRY(BlockJob) txn_list;
diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h
index f7ab183a39..c9b23b0cc9 100644
--- a/include/block/blockjob_int.h
+++ b/include/block/blockjob_int.h
@@ -142,8 +142,8 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
  * @ns: How many nanoseconds to stop for.
  *
  * Put the job to sleep (assuming that it wasn't canceled) for @ns
- * %QEMU_CLOCK_REALTIME nanoseconds.  Canceling the job will not interrupt
- * the wait, so the cancel will not process until the coroutine wakes up.
+ * %QEMU_CLOCK_REALTIME nanoseconds.  Canceling the job will immediately
+ * interrupt the wait.
  */
 void block_job_sleep_ns(BlockJob *job, int64_t ns);