diff --git a/README b/README
index 7833b9736523c72c86cf782d15d23bf92d66c387..49a9fd09cd5ffdc3c9b21b0c861441920e2a611e 100644
--- a/README
+++ b/README
@@ -73,7 +73,7 @@ The QEMU website is also maintained under source control.
   git clone git://git.qemu.org/qemu-web.git
   https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/
 
-A 'git-profile' utility was created to make above process less
+A 'git-publish' utility was created to make above process less
 cumbersome, and is highly recommended for making regular contributions,
 or even just for sending consecutive patch series revisions. It also
 requires a working 'git send-email' setup, and by default doesn't
diff --git a/block/block-backend.c b/block/block-backend.c
index b3c790e2bd44e2a77a9c7092e9d31a87e7850624..f2e0a855ff7c03c16595a4159ffbe4c863a1f103 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1150,7 +1150,7 @@ int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
 typedef struct BlkRwCo {
     BlockBackend *blk;
     int64_t offset;
-    QEMUIOVector *qiov;
+    void *iobuf;
     int ret;
     BdrvRequestFlags flags;
 } BlkRwCo;
@@ -1158,17 +1158,19 @@ typedef struct BlkRwCo {
 static void blk_read_entry(void *opaque)
 {
     BlkRwCo *rwco = opaque;
+    QEMUIOVector *qiov = rwco->iobuf;
 
-    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, rwco->qiov->size,
-                              rwco->qiov, rwco->flags);
+    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, qiov->size,
+                              qiov, rwco->flags);
 }
 
 static void blk_write_entry(void *opaque)
 {
     BlkRwCo *rwco = opaque;
+    QEMUIOVector *qiov = rwco->iobuf;
 
-    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, rwco->qiov->size,
-                               rwco->qiov, rwco->flags);
+    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, qiov->size,
+                               qiov, rwco->flags);
 }
 
 static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
@@ -1188,7 +1190,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
     rwco = (BlkRwCo) {
         .blk    = blk,
         .offset = offset,
-        .qiov   = &qiov,
+        .iobuf  = &qiov,
         .flags  = flags,
         .ret    = NOT_DONE,
     };
@@ -1296,7 +1298,7 @@ static void blk_aio_complete_bh(void *opaque)
 }
 
 static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
-                                QEMUIOVector *qiov, CoroutineEntry co_entry,
+                                void *iobuf, CoroutineEntry co_entry,
                                 BdrvRequestFlags flags,
                                 BlockCompletionFunc *cb, void *opaque)
 {
@@ -1308,7 +1310,7 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
     acb->rwco = (BlkRwCo) {
         .blk    = blk,
         .offset = offset,
-        .qiov   = qiov,
+        .iobuf  = iobuf,
         .flags  = flags,
         .ret    = NOT_DONE,
     };
@@ -1331,10 +1333,11 @@ static void blk_aio_read_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
+    QEMUIOVector *qiov = rwco->iobuf;
 
-    assert(rwco->qiov->size == acb->bytes);
+    assert(qiov->size == acb->bytes);
     rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, acb->bytes,
-                              rwco->qiov, rwco->flags);
+                              qiov, rwco->flags);
     blk_aio_complete(acb);
 }
 
@@ -1342,10 +1345,11 @@ static void blk_aio_write_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
+    QEMUIOVector *qiov = rwco->iobuf;
 
-    assert(!rwco->qiov || rwco->qiov->size == acb->bytes);
+    assert(!qiov || qiov->size == acb->bytes);
     rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, acb->bytes,
-                               rwco->qiov, rwco->flags);
+                               qiov, rwco->flags);
     blk_aio_complete(acb);
 }
 
@@ -1474,8 +1478,10 @@ int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
 static void blk_ioctl_entry(void *opaque)
 {
     BlkRwCo *rwco = opaque;
+    QEMUIOVector *qiov = rwco->iobuf;
+
     rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset,
-                             rwco->qiov->iov[0].iov_base);
+                             qiov->iov[0].iov_base);
 }
 
 int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
@@ -1488,24 +1494,15 @@ static void blk_aio_ioctl_entry(void *opaque)
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
 
-    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset,
-                             rwco->qiov->iov[0].iov_base);
+    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset, rwco->iobuf);
+
     blk_aio_complete(acb);
 }
 
 BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
                           BlockCompletionFunc *cb, void *opaque)
 {
-    QEMUIOVector qiov;
-    struct iovec iov;
-
-    iov = (struct iovec) {
-        .iov_base = buf,
-        .iov_len = 0,
-    };
-    qemu_iovec_init_external(&qiov, &iov, 1);
-
-    return blk_aio_prwv(blk, req, 0, &qiov, blk_aio_ioctl_entry, 0, cb, opaque);
+    return blk_aio_prwv(blk, req, 0, buf, blk_aio_ioctl_entry, 0, cb, opaque);
 }
 
 int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
@@ -1949,7 +1946,9 @@ int blk_truncate(BlockBackend *blk, int64_t offset, PreallocMode prealloc,
 static void blk_pdiscard_entry(void *opaque)
 {
     BlkRwCo *rwco = opaque;
-    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, rwco->qiov->size);
+    QEMUIOVector *qiov = rwco->iobuf;
+
+    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, qiov->size);
 }
 
 int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
diff --git a/cpus.c b/cpus.c
index 865cffd025dec0940541ccd094063bacdac79e75..c652da84cf4825225fb51b8bbca924a3ef35c0ef 100644
--- a/cpus.c
+++ b/cpus.c
@@ -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);
 }
 
 /**
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 2cb990997eab339e0fba07038de69d4992f9b8d7..101f32cf66fad6b435c683f2e1ca7f4ee9669324 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -34,6 +34,7 @@ struct VirtIOBlockDataPlane {
     VirtIODevice *vdev;
     QEMUBH *bh;                     /* bh for guest notification */
     unsigned long *batch_notify_vqs;
+    bool batch_notifications;
 
     /* Note that these EventNotifiers are assigned by value.  This is
      * fine as long as you do not call event_notifier_cleanup on them
@@ -47,8 +48,12 @@ struct VirtIOBlockDataPlane {
 /* Raise an interrupt to signal guest, if necessary */
 void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq)
 {
-    set_bit(virtio_get_queue_index(vq), s->batch_notify_vqs);
-    qemu_bh_schedule(s->bh);
+    if (s->batch_notifications) {
+        set_bit(virtio_get_queue_index(vq), s->batch_notify_vqs);
+        qemu_bh_schedule(s->bh);
+    } else {
+        virtio_notify_irqfd(s->vdev, vq);
+    }
 }
 
 static void notify_guest_bh(void *opaque)
@@ -177,6 +182,12 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
 
     s->starting = true;
 
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+        s->batch_notifications = true;
+    } else {
+        s->batch_notifications = false;
+    }
+
     /* Set up guest notifier (irq) */
     r = k->set_guest_notifiers(qbus->parent, nvqs, true);
     if (r != 0) {
@@ -229,6 +240,22 @@ 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 +280,7 @@ 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());
diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c
index 1c33322ba646c97f2b901a131787d6e1624651d6..912e5005d84530a57d44110e065303be4527e245 100644
--- a/hw/scsi/virtio-scsi-dataplane.c
+++ b/hw/scsi/virtio-scsi-dataplane.c
@@ -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 */
diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index a48c744fa874548156bfb0b1969420576fcc1564..f7a39722002f10fa4433c57e3508b92e1083601e 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -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 */
diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h
index 799614ffd272be4db4667d4f7dbc8f9f7e5ef116..8a7ac2c5287d160badc72782fae923f503f29fed 100644
--- a/include/sysemu/iothread.h
+++ b/include/sysemu/iothread.h
@@ -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);
 
 /*
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index d24ad09f37a71d0a29b277618babc9c6fbc246ac..356bfdc1c1cfe6eb35d34600373a49c244afeeb1 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -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 */
diff --git a/iothread.c b/iothread.c
index 2ec5a3bffea4b8b4e493502970bf3471a80ad8be..1b3463cb004aebc698eb9fab88e40ff899034159 100644
--- a/iothread.c
+++ b/iothread.c
@@ -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;
diff --git a/util/aio-wait.c b/util/aio-wait.c
index a487cdb8523a2a1a5af2eec45ef0f0bd532e6d27..975afddf4c08bab34076ba6db64df68f67960665 100644
--- a/util/aio-wait.c
+++ b/util/aio-wait.c
@@ -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);
+}
diff --git a/vl.c b/vl.c
index dae986b352b2442c97690a4d4ee76396ffc92cd0..3ef04ce991fee332ca2faf883114dda6fb87d419 100644
--- a/vl.c
+++ b/vl.c
@@ -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();