diff --git a/block/io.c b/block/io.c
index 343ff1f233909a7910d897457c0c59fb49d1d54f..a69bfc4197f7bbaee104e2ed80526d59d353bfc4 100644
--- a/block/io.c
+++ b/block/io.c
@@ -301,6 +301,7 @@ void bdrv_drain_all(void)
         if (bs->job) {
             block_job_pause(bs->job);
         }
+        bdrv_drain_recurse(bs);
         aio_context_release(aio_context);
 
         if (!g_slist_find(aio_ctxs, aio_context)) {
diff --git a/blockjob.c b/blockjob.c
index a4021818354c09635c4d086df4cd049a16b7d4e5..9fc37ca96577bcaf931ce6f9b3512d24983d95dc 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -296,7 +296,9 @@ static int block_job_finish_sync(BlockJob *job,
         return -EBUSY;
     }
     while (!job->completed) {
-        aio_poll(bdrv_get_aio_context(bs), true);
+        aio_poll(job->deferred_to_main_loop ? qemu_get_aio_context() :
+                                              bdrv_get_aio_context(bs),
+                 true);
     }
     ret = (job->cancelled && job->ret == 0) ? -ECANCELED : job->ret;
     block_job_unref(job);
@@ -470,6 +472,7 @@ static void block_job_defer_to_main_loop_bh(void *opaque)
     aio_context = bdrv_get_aio_context(data->job->bs);
     aio_context_acquire(aio_context);
 
+    data->job->deferred_to_main_loop = false;
     data->fn(data->job, data->opaque);
 
     aio_context_release(aio_context);
@@ -489,6 +492,7 @@ void block_job_defer_to_main_loop(BlockJob *job,
     data->aio_context = bdrv_get_aio_context(job->bs);
     data->fn = fn;
     data->opaque = opaque;
+    job->deferred_to_main_loop = true;
 
     qemu_bh_schedule(data->bh);
 }
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index d84ccd8d2cc548066709a5f8977097ff1da57514..8bedc4936c01b644178b07c9525190da07d4a43e 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -130,6 +130,11 @@ struct BlockJob {
      */
     bool ready;
 
+    /**
+     * Set to true when the job has deferred work to the main loop.
+     */
+    bool deferred_to_main_loop;
+
     /** Status that is published by the query-block-jobs QMP API */
     BlockDeviceIoStatus iostatus;
 
diff --git a/include/qemu/iov.h b/include/qemu/iov.h
index 569b2c2a23f24de82d74cf33e0fb35ef319b958f..28475516eb43a42364667d48272156bba9b326a4 100644
--- a/include/qemu/iov.h
+++ b/include/qemu/iov.h
@@ -39,10 +39,36 @@ size_t iov_size(const struct iovec *iov, const unsigned int iov_cnt);
  * such "large" value is -1 (sinice size_t is unsigned),
  * so specifying `-1' as `bytes' means 'up to the end of iovec'.
  */
-size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
-                    size_t offset, const void *buf, size_t bytes);
-size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
-                  size_t offset, void *buf, size_t bytes);
+size_t iov_from_buf_full(const struct iovec *iov, unsigned int iov_cnt,
+                         size_t offset, const void *buf, size_t bytes);
+size_t iov_to_buf_full(const struct iovec *iov, const unsigned int iov_cnt,
+		       size_t offset, void *buf, size_t bytes);
+
+static inline size_t
+iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
+             size_t offset, const void *buf, size_t bytes)
+{
+    if (__builtin_constant_p(bytes) && iov_cnt &&
+        offset <= iov[0].iov_len && bytes <= iov[0].iov_len - offset) {
+        memcpy(iov[0].iov_base + offset, buf, bytes);
+        return bytes;
+    } else {
+        return iov_from_buf_full(iov, iov_cnt, offset, buf, bytes);
+    }
+}
+
+static inline size_t
+iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
+           size_t offset, void *buf, size_t bytes)
+{
+    if (__builtin_constant_p(bytes) && iov_cnt &&
+        offset <= iov[0].iov_len && bytes <= iov[0].iov_len - offset) {
+        memcpy(buf, iov[0].iov_base + offset, bytes);
+        return bytes;
+    } else {
+        return iov_to_buf_full(iov, iov_cnt, offset, buf, bytes);
+    }
+}
 
 /**
  * Set data bytes pointed out by iovec `iov' of size `iov_cnt' elements,
diff --git a/util/iov.c b/util/iov.c
index e802ee15bcb9d74be37de710ffd0eb741ddfe2d8..062f4e50c36099aa221da7be2f77c167aca68753 100644
--- a/util/iov.c
+++ b/util/iov.c
@@ -20,8 +20,8 @@
 #include "qemu/iov.h"
 #include "qemu/sockets.h"
 
-size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
-                    size_t offset, const void *buf, size_t bytes)
+size_t iov_from_buf_full(const struct iovec *iov, unsigned int iov_cnt,
+                         size_t offset, const void *buf, size_t bytes)
 {
     size_t done;
     unsigned int i;
@@ -39,8 +39,8 @@ size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
     return done;
 }
 
-size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
-                  size_t offset, void *buf, size_t bytes)
+size_t iov_to_buf_full(const struct iovec *iov, const unsigned int iov_cnt,
+                       size_t offset, void *buf, size_t bytes)
 {
     size_t done;
     unsigned int i;