diff --git a/block/qcow2.c b/block/qcow2.c
index 4a89850389..4b4a0ce6e0 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -2168,11 +2168,20 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
         ret = qcow2_alloc_cluster_offset(bs, offset, &cur_bytes,
                                          &cluster_offset, &l2meta);
         if (ret < 0) {
-            goto fail;
+            goto out_locked;
         }
 
         assert((cluster_offset & 511) == 0);
 
+        ret = qcow2_pre_write_overlap_check(bs, 0,
+                                            cluster_offset + offset_in_cluster,
+                                            cur_bytes, true);
+        if (ret < 0) {
+            goto out_locked;
+        }
+
+        qemu_co_mutex_unlock(&s->lock);
+
         qemu_iovec_reset(&hd_qiov);
         qemu_iovec_concat(&hd_qiov, qiov, bytes_done, cur_bytes);
 
@@ -2184,7 +2193,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
                                                    * s->cluster_size);
                 if (cluster_data == NULL) {
                     ret = -ENOMEM;
-                    goto fail;
+                    goto out_unlocked;
                 }
             }
 
@@ -2199,40 +2208,34 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
                                       cluster_data,
                                       cur_bytes, NULL) < 0) {
                 ret = -EIO;
-                goto fail;
+                goto out_unlocked;
             }
 
             qemu_iovec_reset(&hd_qiov);
             qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes);
         }
 
-        ret = qcow2_pre_write_overlap_check(bs, 0,
-                cluster_offset + offset_in_cluster, cur_bytes, true);
-        if (ret < 0) {
-            goto fail;
-        }
-
         /* If we need to do COW, check if it's possible to merge the
          * writing of the guest data together with that of the COW regions.
          * If it's not possible (or not necessary) then write the
          * guest data now. */
         if (!merge_cow(offset, cur_bytes, &hd_qiov, l2meta)) {
-            qemu_co_mutex_unlock(&s->lock);
             BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
             trace_qcow2_writev_data(qemu_coroutine_self(),
                                     cluster_offset + offset_in_cluster);
             ret = bdrv_co_pwritev(s->data_file,
                                   cluster_offset + offset_in_cluster,
                                   cur_bytes, &hd_qiov, 0);
-            qemu_co_mutex_lock(&s->lock);
             if (ret < 0) {
-                goto fail;
+                goto out_unlocked;
             }
         }
 
+        qemu_co_mutex_lock(&s->lock);
+
         ret = qcow2_handle_l2meta(bs, &l2meta, true);
         if (ret) {
-            goto fail;
+            goto out_locked;
         }
 
         bytes -= cur_bytes;
@@ -2241,8 +2244,12 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
         trace_qcow2_writev_done_part(qemu_coroutine_self(), cur_bytes);
     }
     ret = 0;
+    goto out_locked;
 
-fail:
+out_unlocked:
+    qemu_co_mutex_lock(&s->lock);
+
+out_locked:
     qcow2_handle_l2meta(bs, &l2meta, false);
 
     qemu_co_mutex_unlock(&s->lock);