qcow2: Batch discards

This optimises the discard operation for freed clusters by batching
discard requests (both snapshot deletion and bdrv_discard end up
updating the refcounts cluster by cluster).

Note that we don't discard asynchronously, but keep s->lock held. This
is to avoid that a freed cluster is reallocated and written to while the
discard is still in flight.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index 3191d6b..cca76d4 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -1377,18 +1377,25 @@
 
     nb_clusters = size_to_clusters(s, end_offset - offset);
 
+    s->cache_discards = true;
+
     /* Each L2 table is handled by its own loop iteration */
     while (nb_clusters > 0) {
         ret = discard_single_l2(bs, offset, nb_clusters);
         if (ret < 0) {
-            return ret;
+            goto fail;
         }
 
         nb_clusters -= ret;
         offset += (ret * s->cluster_size);
     }
 
-    return 0;
+    ret = 0;
+fail:
+    s->cache_discards = false;
+    qcow2_process_discards(bs, ret);
+
+    return ret;
 }
 
 /*
@@ -1450,15 +1457,22 @@
     /* Each L2 table is handled by its own loop iteration */
     nb_clusters = size_to_clusters(s, nb_sectors << BDRV_SECTOR_BITS);
 
+    s->cache_discards = true;
+
     while (nb_clusters > 0) {
         ret = zero_single_l2(bs, offset, nb_clusters);
         if (ret < 0) {
-            return ret;
+            goto fail;
         }
 
         nb_clusters -= ret;
         offset += (ret * s->cluster_size);
     }
 
-    return 0;
+    ret = 0;
+fail:
+    s->cache_discards = false;
+    qcow2_process_discards(bs, ret);
+
+    return ret;
 }