diff --git a/block.c b/block.c
index c05875fe39..c7a1a3c85c 100644
--- a/block.c
+++ b/block.c
@@ -3778,12 +3778,20 @@ typedef struct BlockDriverAIOCBCoroutine {
     BlockDriverAIOCB common;
     BlockRequest req;
     bool is_write;
+    bool *done;
     QEMUBH* bh;
 } BlockDriverAIOCBCoroutine;
 
 static void bdrv_aio_co_cancel_em(BlockDriverAIOCB *blockacb)
 {
-    qemu_aio_flush();
+    BlockDriverAIOCBCoroutine *acb =
+        container_of(blockacb, BlockDriverAIOCBCoroutine, common);
+    bool done = false;
+
+    acb->done = &done;
+    while (!done) {
+        qemu_aio_wait();
+    }
 }
 
 static const AIOCBInfo bdrv_em_co_aiocb_info = {
@@ -3796,6 +3804,11 @@ static void bdrv_co_em_bh(void *opaque)
     BlockDriverAIOCBCoroutine *acb = opaque;
 
     acb->common.cb(acb->common.opaque, acb->req.error);
+
+    if (acb->done) {
+        *acb->done = true;
+    }
+
     qemu_bh_delete(acb->bh);
     qemu_aio_release(acb);
 }
@@ -3834,6 +3847,7 @@ static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
     acb->req.nb_sectors = nb_sectors;
     acb->req.qiov = qiov;
     acb->is_write = is_write;
+    acb->done = NULL;
 
     co = qemu_coroutine_create(bdrv_co_do_rw);
     qemu_coroutine_enter(co, acb);
@@ -3860,6 +3874,8 @@ BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
     BlockDriverAIOCBCoroutine *acb;
 
     acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+    acb->done = NULL;
+
     co = qemu_coroutine_create(bdrv_aio_flush_co_entry);
     qemu_coroutine_enter(co, acb);
 
@@ -3888,6 +3904,7 @@ BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
     acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
     acb->req.sector = sector_num;
     acb->req.nb_sectors = nb_sectors;
+    acb->done = NULL;
     co = qemu_coroutine_create(bdrv_aio_discard_co_entry);
     qemu_coroutine_enter(co, acb);