vl: introduce vm_shutdown()

index a48c744fa8..f7a3972200 100644
@@ -113,4 +113,17 @@ typedef struct {
  */
 void aio_wait_kick(AioWait *wait);
 
+/**
+ * aio_wait_bh_oneshot:
+ * @ctx: the aio context
+ * @cb: the BH callback function
+ * @opaque: user data for the BH callback function
+ *
+ * Run a BH in @ctx and wait for it to complete.
+ *
+ * Must be called from the main loop thread with @ctx acquired exactly once.
+ * Note that main loop event processing may occur.
+ */
+void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
+
 #endif /* QEMU_AIO_WAIT */

index a487cdb852..975afddf4c 100644
@@ -38,3 +38,34 @@ void aio_wait_kick(AioWait *wait)
         aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL);
     }
 }
+
+typedef struct {
+    AioWait wait;
+    bool done;
+    QEMUBHFunc *cb;
+    void *opaque;
+} AioWaitBHData;
+
+/* Context: BH in IOThread */
+static void aio_wait_bh(void *opaque)
+{
+    AioWaitBHData *data = opaque;
+
+    data->cb(data->opaque);
+
+    data->done = true;
+    aio_wait_kick(&data->wait);
+}
+
+void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
+{
+    AioWaitBHData data = {
+        .cb = cb,
+        .opaque = opaque,
+    };
+
+    assert(qemu_get_current_aio_context() == qemu_get_aio_context());
+
+    aio_bh_schedule_oneshot(ctx, aio_wait_bh, &data);
+    AIO_WAIT_WHILE(&data.wait, ctx, !data.done);
+}

index 2cb990997e..d3bb09bc4e 100644
@@ -229,6 +229,22 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
     return -ENOSYS;
 }
 
+/* Stop notifications for new requests from guest.
+ *
+ * Context: BH in IOThread
+ */
+static void virtio_blk_data_plane_stop_bh(void *opaque)
+{
+    VirtIOBlockDataPlane *s = opaque;
+    unsigned i;
+
+    for (i = 0; i < s->conf->num_queues; i++) {
+        VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+        virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, NULL);
+    }
+}
+
 /* Context: QEMU global mutex held */
 void virtio_blk_data_plane_stop(VirtIODevice *vdev)
 {

@@ -253,13 +269,7 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
     trace_virtio_blk_data_plane_stop(s);
 
     aio_context_acquire(s->ctx);
-
-    /* Stop notifications for new requests from guest */
-    for (i = 0; i < nvqs; i++) {
-        VirtQueue *vq = virtio_get_queue(s->vdev, i);
-
-        virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, NULL);
-    }
+    aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
 
     /* Drain and switch bs back to the QEMU main loop */
     blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());

index 1c33322ba6..912e5005d8 100644
@@ -107,9 +107,10 @@ static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n,
     return 0;
 }
 
-/* assumes s->ctx held */
-static void virtio_scsi_clear_aio(VirtIOSCSI *s)
+/* Context: BH in IOThread */
+static void virtio_scsi_dataplane_stop_bh(void *opaque)
 {
+    VirtIOSCSI *s = opaque;
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
     int i;
 

@@ -171,7 +172,7 @@ int virtio_scsi_dataplane_start(VirtIODevice *vdev)
     return 0;
 
 fail_vrings:
-    virtio_scsi_clear_aio(s);
+    aio_wait_bh_oneshot(s->ctx, virtio_scsi_dataplane_stop_bh, s);
     aio_context_release(s->ctx);
     for (i = 0; i < vs->conf.num_queues + 2; i++) {
         virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);

@@ -207,7 +208,7 @@ void virtio_scsi_dataplane_stop(VirtIODevice *vdev)
     s->dataplane_stopping = true;
 
     aio_context_acquire(s->ctx);
-    virtio_scsi_clear_aio(s);
+    aio_wait_bh_oneshot(s->ctx, virtio_scsi_dataplane_stop_bh, s);
     aio_context_release(s->ctx);
 
     blk_drain_all(); /* ensure there are no in-flight requests */

index 799614ffd2..8a7ac2c528 100644
@@ -45,7 +45,6 @@ typedef struct {
 char *iothread_get_id(IOThread *iothread);
 IOThread *iothread_by_id(const char *id);
 AioContext *iothread_get_aio_context(IOThread *iothread);
-void iothread_stop_all(void);
 GMainContext *iothread_get_g_main_context(IOThread *iothread);
 
 /*

index d24ad09f37..356bfdc1c1 100644
@@ -56,6 +56,7 @@ void vm_start(void);
 int vm_prepare_start(void);
 int vm_stop(RunState state);
 int vm_stop_force_state(RunState state);
+int vm_shutdown(void);
 
 typedef enum WakeupReason {
     /* Always keep QEMU_WAKEUP_REASON_NONE = 0 */

index 9bcff7d63c..d8fe90eafe 100644
@@ -993,7 +993,7 @@ void cpu_synchronize_all_pre_loadvm(void)
     }
 }
 
-static int do_vm_stop(RunState state)
+static int do_vm_stop(RunState state, bool send_stop)
 {
     int ret = 0;
 

@@ -1002,7 +1002,9 @@ static int do_vm_stop(RunState state)
         pause_all_vcpus();
         runstate_set(state);
         vm_state_notify(0, state);
-        qapi_event_send_stop(&error_abort);
+        if (send_stop) {
+            qapi_event_send_stop(&error_abort);
+        }
     }
 
     bdrv_drain_all();

@@ -1012,6 +1014,14 @@ static int do_vm_stop(RunState state)
     return ret;
 }
 
+/* Special vm_stop() variant for terminating the process.  Historically clients
+ * did not expect a QMP STOP event and so we need to retain compatibility.
+ */
+int vm_shutdown(void)
+{
+    return do_vm_stop(RUN_STATE_SHUTDOWN, false);
+}
+
 static bool cpu_can_run(CPUState *cpu)
 {
     if (cpu->stop) {

@@ -1994,7 +2004,7 @@ int vm_stop(RunState state)
         return 0;
     }
 
-    return do_vm_stop(state);
+    return do_vm_stop(state, true);
 }
 
 /**

index 2ec5a3bffe..1b3463cb00 100644
@@ -101,18 +101,6 @@ void iothread_stop(IOThread *iothread)
     qemu_thread_join(&iothread->thread);
 }
 
-static int iothread_stop_iter(Object *object, void *opaque)
-{
-    IOThread *iothread;
-
-    iothread = (IOThread *)object_dynamic_cast(object, TYPE_IOTHREAD);
-    if (!iothread) {
-        return 0;
-    }
-    iothread_stop(iothread);
-    return 0;
-}
-
 static void iothread_instance_init(Object *obj)
 {
     IOThread *iothread = IOTHREAD(obj);

@@ -333,25 +321,6 @@ IOThreadInfoList *qmp_query_iothreads(Error **errp)
     return head;
 }
 
-void iothread_stop_all(void)
-{
-    Object *container = object_get_objects_root();
-    BlockDriverState *bs;
-    BdrvNextIterator it;
-
-    for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-        if (ctx == qemu_get_aio_context()) {
-            continue;
-        }
-        aio_context_acquire(ctx);
-        bdrv_set_aio_context(bs, qemu_get_aio_context());
-        aio_context_release(ctx);
-    }
-
-    object_child_foreach(container, iothread_stop_iter, NULL);
-}
-
 static gpointer iothread_g_main_context_init(gpointer opaque)
 {
     AioContext *ctx;

index dae986b352..3ef04ce991 100644
@@ -4722,17 +4722,10 @@ int main(int argc, char **argv, char **envp)
     os_setup_post();
 
     main_loop();
-    replay_disable_events();
 
-    /* The ordering of the following is delicate.  Stop vcpus to prevent new
-     * I/O requests being queued by the guest.  Then stop IOThreads (this
-     * includes a drain operation and completes all request processing).  At
-     * this point emulated devices are still associated with their IOThreads
-     * (if any) but no longer have any work to do.  Only then can we close
-     * block devices safely because we know there is no more I/O coming.
-     */
-    pause_all_vcpus();
-    iothread_stop_all();
+    /* No more vcpu or device emulation activity beyond this point */
+    vm_shutdown();
+
     bdrv_close_all();
 
     res_free();