copy-before-write: allow specifying minimum cluster size

In the context of backup fleecing, discarding the source will not work
when the fleecing image has a larger granularity than the one used for
block-copy operations (can happen if the backup target has smaller
cluster size), because cbw_co_pdiscard_snapshot() will align down the
discard requests and thus effectively ignore then.

To make @discard-source work in such a scenario, allow specifying the
minimum cluster size used for block-copy operations and thus in
particular also the granularity for discard requests to the source.

The type 'size' (corresponding to uint64_t in C) is used in QAPI to
rule out negative inputs and for consistency with already existing
@cluster-size parameters. Since block_copy_calculate_cluster_size()
uses int64_t for its result, a check that the input is not too large
is added in block_copy_state_new() before calling it. The calculation
in block_copy_calculate_cluster_size() is done in the target int64_t
type.

Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Acked-by: Markus Armbruster <armbru@redhat.com> (QAPI schema)
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Message-Id: <20240711120915.310243-2-f.ebner@proxmox.com>
[vsementsov: switch version to 9.2 in QAPI doc]
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>

block/block-copy.c

@@ -310,6 +310,7 @@ void block_copy_set_copy_opts(BlockCopyState *s, bool use_copy_range,
 }
 
 static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
+                                                 int64_t min_cluster_size,
                                                  Error **errp)
 {
     int ret;
@@ -319,6 +320,9 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
     GLOBAL_STATE_CODE();
     GRAPH_RDLOCK_GUARD_MAINLOOP();
 
+    min_cluster_size = MAX(min_cluster_size,
+                           (int64_t)BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
+
     target_does_cow = bdrv_backing_chain_next(target);
 
     /*
@@ -329,13 +333,13 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
     ret = bdrv_get_info(target, &bdi);
     if (ret == -ENOTSUP && !target_does_cow) {
         /* Cluster size is not defined */
-        warn_report("The target block device doesn't provide "
+        warn_report("The target block device doesn't provide information about "
-                    "information about the block size and it doesn't have a "
+                    "the block size and it doesn't have a backing file. The "
-                    "backing file. The default block size of %u bytes is "
+                    "(default) block size of %" PRIi64 " bytes is used. If the "
-                    "used. If the actual block size of the target exceeds "
+                    "actual block size of the target exceeds this value, the "
-                    "this default, the backup may be unusable",
+                    "backup may be unusable",
-                    BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
+                    min_cluster_size);
-        return BLOCK_COPY_CLUSTER_SIZE_DEFAULT;
+        return min_cluster_size;
     } else if (ret < 0 && !target_does_cow) {
         error_setg_errno(errp, -ret,
             "Couldn't determine the cluster size of the target image, "
@@ -345,16 +349,17 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
         return ret;
     } else if (ret < 0 && target_does_cow) {
         /* Not fatal; just trudge on ahead. */
-        return BLOCK_COPY_CLUSTER_SIZE_DEFAULT;
+        return min_cluster_size;
     }
 
-    return MAX(BLOCK_COPY_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
+    return MAX(min_cluster_size, bdi.cluster_size);
 }
 
 BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
                                      BlockDriverState *copy_bitmap_bs,
                                      const BdrvDirtyBitmap *bitmap,
                                      bool discard_source,
+                                     uint64_t min_cluster_size,
                                      Error **errp)
 {
     ERRP_GUARD();
@@ -365,7 +370,18 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
 
     GLOBAL_STATE_CODE();
 
-    cluster_size = block_copy_calculate_cluster_size(target->bs, errp);
+    if (min_cluster_size > INT64_MAX) {
+        error_setg(errp, "min-cluster-size too large: %" PRIu64 " > %" PRIi64,
+                   min_cluster_size, INT64_MAX);
+        return NULL;
+    } else if (min_cluster_size && !is_power_of_2(min_cluster_size)) {
+        error_setg(errp, "min-cluster-size needs to be a power of 2");
+        return NULL;
+    }
+
+    cluster_size = block_copy_calculate_cluster_size(target->bs,
+                                                     (int64_t)min_cluster_size,
+                                                     errp);
     if (cluster_size < 0) {
         return NULL;
     }

block/copy-before-write.c

@@ -417,6 +417,7 @@ static BlockdevOptions *cbw_parse_options(QDict *options, Error **errp)
     qdict_extract_subqdict(options, NULL, "bitmap");
     qdict_del(options, "on-cbw-error");
     qdict_del(options, "cbw-timeout");
+    qdict_del(options, "min-cluster-size");
 
 out:
     visit_free(v);
@@ -476,8 +477,10 @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
              bs->file->bs->supported_zero_flags);
 
     s->discard_source = flags & BDRV_O_CBW_DISCARD_SOURCE;
+
     s->bcs = block_copy_state_new(bs->file, s->target, bs, bitmap,
-                                  flags & BDRV_O_CBW_DISCARD_SOURCE, errp);
+                                  flags & BDRV_O_CBW_DISCARD_SOURCE,
+                                  opts->min_cluster_size, errp);
     if (!s->bcs) {
         error_prepend(errp, "Cannot create block-copy-state: ");
         return -EINVAL;

include/block/block-copy.h

@@ -28,6 +28,7 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
                                      BlockDriverState *copy_bitmap_bs,
                                      const BdrvDirtyBitmap *bitmap,
                                      bool discard_source,
+                                     uint64_t min_cluster_size,
                                      Error **errp);
 
 /* Function should be called prior any actual copy request */

qapi/block-core.json

@@ -4639,12 +4639,18 @@
 #     @on-cbw-error parameter will decide how this failure is handled.
 #     Default 0.  (Since 7.1)
 #
+# @min-cluster-size: Minimum size of blocks used by copy-before-write
+#     operations.  Has to be a power of 2.  No effect if smaller than
+#     the maximum of the target's cluster size and 64 KiB.  Default 0.
+#     (Since 9.2)
+#
 # Since: 6.2
 ##
 { 'struct': 'BlockdevOptionsCbw',
   'base': 'BlockdevOptionsGenericFormat',
   'data': { 'target': 'BlockdevRef', '*bitmap': 'BlockDirtyBitmap',
-            '*on-cbw-error': 'OnCbwError', '*cbw-timeout': 'uint32' } }
+            '*on-cbw-error': 'OnCbwError', '*cbw-timeout': 'uint32',
+            '*min-cluster-size': 'size' } }
 
 ##
 # @BlockdevOptions: