[Qemu-devel] [PATCH v4 1/3] block: add bdrv_get_format_alloc_stat format interface

[Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>]

The function should collect statistics, about used/unused by top-level
format driver space (in its .file) and allocation status
(data/zero/discarded/after-eof) of corresponding areas in this .file.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
---
 block.c                   | 16 +++++++++++
 include/block/block.h     |  3 ++
 include/block/block_int.h |  2 ++
 qapi/block-core.json      | 72 +++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 93 insertions(+)

diff --git a/block.c b/block.c
index 50ba264143..7d720ae0c2 100644
--- a/block.c
+++ b/block.c
@@ -3407,6 +3407,22 @@ int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
 }
 
 /**
+ * Collect format allocation info. See BlockFormatAllocInfo definition in
+ * qapi/block-core.json.
+ */
+int bdrv_get_format_alloc_stat(BlockDriverState *bs, BlockFormatAllocInfo *bfai)
+{
+    BlockDriver *drv = bs->drv;
+    if (!drv) {
+        return -ENOMEDIUM;
+    }
+    if (drv->bdrv_get_format_alloc_stat) {
+        return drv->bdrv_get_format_alloc_stat(bs, bfai);
+    }
+    return -ENOTSUP;
+}
+
+/**
  * Return number of sectors on success, -errno on error.
  */
 int64_t bdrv_nb_sectors(BlockDriverState *bs)
diff --git a/include/block/block.h b/include/block/block.h
index 9b355e92d8..646376a772 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -335,6 +335,9 @@ typedef enum {
 
 int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix);
 
+int bdrv_get_format_alloc_stat(BlockDriverState *bs,
+                               BlockFormatAllocInfo *bfai);
+
 /* The units of offset and total_work_size may be chosen arbitrarily by the
  * block driver; total_work_size may change during the course of the amendment
  * operation */
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 8d3724cce6..458c715e99 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -208,6 +208,8 @@ struct BlockDriver {
     int64_t (*bdrv_getlength)(BlockDriverState *bs);
     bool has_variable_length;
     int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
+    int (*bdrv_get_format_alloc_stat)(BlockDriverState *bs,
+                                      BlockFormatAllocInfo *bfai);
 
     int coroutine_fn (*bdrv_co_pwritev_compressed)(BlockDriverState *bs,
         uint64_t offset, uint64_t bytes, QEMUIOVector *qiov);
diff --git a/qapi/block-core.json b/qapi/block-core.json
index ea0b3e8b13..93f6995381 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -139,6 +139,78 @@
            '*format-specific': 'ImageInfoSpecific' } }
 
 ##
+# @BlockFormatAllocInfo:
+#
+#
+# Allocation information of an underlying protocol file, as partitioned by a
+# format driver's utilization of said allocations.
+# All fields are in bytes.
+#
+# Regions of the underlying protocol file may be considered used or unused by
+# the format driver interpreting these regions. It is at the discretion of the
+# format driver (e.g. qcow2) which regions of its backing storage are considered
+# in-use or not.
+#
+# For now, the only format driver supporting this feature is Qcow2 which is a
+# cluster based format. Clusters considered in-use by qcow2 are those with a
+# non-zero refcount in the format metadata. All other clusters, if present, are
+# considered unused. Examples of unused allocations for the Qcow2 format are
+# leaked clusters, pre-allocated clusters, and recently freed clusters.
+#
+# Note: the whole underlying protocol file is described as well as all format
+# file allocations, not only virtual disk data (metadata, internal snapshots,
+# etc. are included).
+#
+# For the underlying protocol file there are native block-status types of the
+# regions:
+#  - data: allocated data
+#  - zero: reported as zero (for example, this type corresponds to holes for
+#          POSIX files on sparce file-system)
+#  - discarded: not allocated
+# 4th additional type is 'overrun', is data referenced by the format driver
+# located beyond EOF of the underlying protocol file. For example, a partially
+# allocated cluster at the end of a QCOW2 file, where Qcow2 generally operates
+# on complete clusters.
+#
+# So, the fields are:
+#
+# @used-data: used by the format file and backed by data in the underlying
+#             protocol file
+#
+# @used-zero: used by the format file and backed by zeroes in the underlying
+#             protocol file; which may be a filesystem hole for POSIX files.
+#
+# @used-discarded: used by the format file but actually unallocated in the
+#                  underlying protocol file
+#
+# @used-overrun: used by the format file beyond the end of the underlying
+#                protocol file
+#
+# @unused-data: allocated data in the underlying protocol file not used by the
+#               format file
+#
+# @unused-zero: reported-as-zero regions in the underlying protocol file not
+#               used by the format file
+#
+# @unused-discarded: unallocated areas in the underlying protocol file not used
+#                    by the format file
+#
+# Note: sum of 6 fields {used,unused}-{data,zero,discarded} is equal to the
+#       length of the underlying protocol file.
+#
+# Since: 2.11
+#
+##
+{ 'struct': 'BlockFormatAllocInfo',
+  'data': {'used-data':        'uint64',
+           'used-zero':        'uint64',
+           'used-discarded':   'uint64',
+           'used-overrun':     'uint64',
+           'unused-data':      'uint64',
+           'unused-zero':      'uint64',
+           'unused-discarded': 'uint64' } }
+
+##
 # @ImageCheck:
 #
 # Information about a QEMU image file check
-- 
2.11.1