qcow2: Allow "full" discard

Normally, discarded sectors should read back as zero. However, there are
cases in which a sector (or rather cluster) should be discarded as if
they were never written in the first place, that is, reading them should
fall through to the backing file again.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Message-id: 1414159063-25977-2-git-send-email-mreitz@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

block/qcow2-cluster.c

@@ -1414,7 +1414,7 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
  * clusters.
  */
 static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
-    unsigned int nb_clusters, enum qcow2_discard_type type)
+    unsigned int nb_clusters, enum qcow2_discard_type type, bool full_discard)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t *l2_table;
@@ -1436,23 +1436,30 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
         old_l2_entry = be64_to_cpu(l2_table[l2_index + i]);
 
         /*
-         * Make sure that a discarded area reads back as zeroes for v3 images
+         * If full_discard is false, make sure that a discarded area reads back
-         * (we cannot do it for v2 without actually writing a zero-filled
+         * as zeroes for v3 images (we cannot do it for v2 without actually
-         * buffer). We can skip the operation if the cluster is already marked
+         * writing a zero-filled buffer). We can skip the operation if the
-         * as zero, or if it's unallocated and we don't have a backing file.
+         * cluster is already marked as zero, or if it's unallocated and we
+         * don't have a backing file.
          *
          * TODO We might want to use bdrv_get_block_status(bs) here, but we're
          * holding s->lock, so that doesn't work today.
+         *
+         * If full_discard is true, the sector should not read back as zeroes,
+         * but rather fall through to the backing file.
          */
         switch (qcow2_get_cluster_type(old_l2_entry)) {
             case QCOW2_CLUSTER_UNALLOCATED:
-                if (!bs->backing_hd) {
+                if (full_discard || !bs->backing_hd) {
                     continue;
                 }
                 break;
 
             case QCOW2_CLUSTER_ZERO:
-                continue;
+                if (!full_discard) {
+                    continue;
+                }
+                break;
 
             case QCOW2_CLUSTER_NORMAL:
             case QCOW2_CLUSTER_COMPRESSED:
@@ -1464,7 +1471,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
 
         /* First remove L2 entries */
         qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
-        if (s->qcow_version >= 3) {
+        if (!full_discard && s->qcow_version >= 3) {
             l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
         } else {
             l2_table[l2_index + i] = cpu_to_be64(0);
@@ -1483,7 +1490,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
 }
 
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
-    int nb_sectors, enum qcow2_discard_type type)
+    int nb_sectors, enum qcow2_discard_type type, bool full_discard)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t end_offset;
@@ -1506,7 +1513,7 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 
     /* Each L2 table is handled by its own loop iteration */
     while (nb_clusters > 0) {
-        ret = discard_single_l2(bs, offset, nb_clusters, type);
+        ret = discard_single_l2(bs, offset, nb_clusters, type, full_discard);
         if (ret < 0) {
             goto fail;
         }

block/qcow2-snapshot.c

@@ -441,7 +441,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     qcow2_discard_clusters(bs, qcow2_vm_state_offset(s),
                            align_offset(sn->vm_state_size, s->cluster_size)
                                 >> BDRV_SECTOR_BITS,
-                           QCOW2_DISCARD_NEVER);
+                           QCOW2_DISCARD_NEVER, false);
 
 #ifdef DEBUG_ALLOC
     {

block/qcow2.c

@@ -2089,7 +2089,7 @@ static coroutine_fn int qcow2_co_discard(BlockDriverState *bs,
 
     qemu_co_mutex_lock(&s->lock);
     ret = qcow2_discard_clusters(bs, sector_num << BDRV_SECTOR_BITS,
-        nb_sectors, QCOW2_DISCARD_REQUEST);
+        nb_sectors, QCOW2_DISCARD_REQUEST, false);
     qemu_co_mutex_unlock(&s->lock);
     return ret;
 }

block/qcow2.h

@@ -534,7 +534,7 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
 
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
-    int nb_sectors, enum qcow2_discard_type type);
+    int nb_sectors, enum qcow2_discard_type type, bool full_discard);
 int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
 
 int qcow2_expand_zero_clusters(BlockDriverState *bs);