Merge remote-tracking branch 'remotes/maxreitz/tags/pull-block-2021-03-30' into staging

Block patches for 6.0-rc1:
- Mark the qcow2 cache clean timer as external to fix record/replay
- Fix the mirror filter node's permissions so that an external process
  cannot grab an image while it is used as the mirror source
- Add documentation about FUSE exports to the storage daemon
- When creating a qcow2 image with the data-file-raw option, all
  metadata structures should be preallocated
- iotest fixes

# gpg: Signature made Tue 30 Mar 2021 13:38:40 BST
# gpg:                using RSA key 91BEB60A30DB3E8857D11829F407DB0061D5CF40
# gpg:                issuer "mreitz@redhat.com"
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>" [full]
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/maxreitz/tags/pull-block-2021-03-30:
  iotests/244: Test preallocation for data-file-raw
  qcow2: Force preallocation with data-file-raw
  qsd: Document FUSE exports
  block/mirror: Fix mirror_top's permissions
  iotests/046: Filter request length
  qcow2: use external virtual timers
  iotests/116: Fix reference output
  iotests: fix 051.out expected output after error text touchups
  iotests: Fix typo in iotest 051

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

12 files changed, 319 insertions, 80 deletions

diff --git a/block/mirror.c b/block/mirror.c
index 6af02a57c4..d7e54c0ff7 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -89,6 +89,7 @@ typedef struct MirrorBlockJob {
 typedef struct MirrorBDSOpaque {
     MirrorBlockJob *job;
     bool stop;
+    bool is_commit;
 } MirrorBDSOpaque;
 
 struct MirrorOp {
@@ -1522,13 +1523,27 @@ static void bdrv_mirror_top_child_perm(BlockDriverState *bs, BdrvChild *c,
         return;
     }
 
-    /* Must be able to forward guest writes to the real image */
-    *nperm = 0;
-    if (perm & BLK_PERM_WRITE) {
-        *nperm |= BLK_PERM_WRITE;
-    }
+    bdrv_default_perms(bs, c, role, reopen_queue,
+                       perm, shared, nperm, nshared);
 
-    *nshared = BLK_PERM_ALL;
+    if (s->is_commit) {
+        /*
+         * For commit jobs, we cannot take CONSISTENT_READ, because
+         * that permission is unshared for everything above the base
+         * node (except for filters on the base node).
+         * We also have to force-share the WRITE permission, or
+         * otherwise we would block ourselves at the base node (if
+         * writes are blocked for a node, they are also blocked for
+         * its backing file).
+         * (We could also share RESIZE, because it may be needed for
+         * the target if its size is less than the top node's; but
+         * bdrv_default_perms_for_cow() automatically shares RESIZE
+         * for backing nodes if WRITE is shared, so there is no need
+         * to do it here.)
+         */
+        *nperm &= ~BLK_PERM_CONSISTENT_READ;
+        *nshared |= BLK_PERM_WRITE;
+    }
 }
 
 /* Dummy node that provides consistent read to its users without requiring it
@@ -1591,6 +1606,8 @@ static BlockJob *mirror_start_job(
         return NULL;
     }
 
+    target_is_backing = bdrv_chain_contains(bs, target);
+
     /* In the case of active commit, add dummy driver to provide consistent
      * reads on the top, while disabling it in the intermediate nodes, and make
      * the backing chain writable. */
@@ -1613,6 +1630,8 @@ static BlockJob *mirror_start_job(
     bs_opaque = g_new0(MirrorBDSOpaque, 1);
     mirror_top_bs->opaque = bs_opaque;
 
+    bs_opaque->is_commit = target_is_backing;
+
     /* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
      * it alive until block_job_create() succeeds even if bs has no parent. */
     bdrv_ref(mirror_top_bs);
@@ -1653,7 +1672,6 @@ static BlockJob *mirror_start_job(
     target_perms = BLK_PERM_WRITE;
     target_shared_perms = BLK_PERM_WRITE_UNCHANGED;
 
-    target_is_backing = bdrv_chain_contains(bs, target);
     if (target_is_backing) {
         int64_t bs_size, target_size;
         bs_size = bdrv_getlength(bs);
diff --git a/block/qcow2.c b/block/qcow2.c
index 0db1227ac9..9727ae8fe3 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -840,9 +840,10 @@ static void cache_clean_timer_init(BlockDriverState *bs, AioContext *context)
 {
     BDRVQcow2State *s = bs->opaque;
     if (s->cache_clean_interval > 0) {
-        s->cache_clean_timer = aio_timer_new(context, QEMU_CLOCK_VIRTUAL,
-                                             SCALE_MS, cache_clean_timer_cb,
-                                             bs);
+        s->cache_clean_timer =
+            aio_timer_new_with_attrs(context, QEMU_CLOCK_VIRTUAL,
+                                     SCALE_MS, QEMU_TIMER_ATTR_EXTERNAL,
+                                     cache_clean_timer_cb, bs);
         timer_mod(s->cache_clean_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
                   (int64_t) s->cache_clean_interval * 1000);
     }
@@ -3502,6 +3503,28 @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp)
         ret = -EINVAL;
         goto out;
     }
+    if (qcow2_opts->data_file_raw &&
+        qcow2_opts->preallocation == PREALLOC_MODE_OFF)
+    {
+        /*
+         * data-file-raw means that "the external data file can be
+         * read as a consistent standalone raw image without looking
+         * at the qcow2 metadata."  It does not say that the metadata
+         * must be ignored, though (and the qcow2 driver in fact does
+         * not ignore it), so the L1/L2 tables must be present and
+         * give a 1:1 mapping, so you get the same result regardless
+         * of whether you look at the metadata or whether you ignore
+         * it.
+         */
+        qcow2_opts->preallocation = PREALLOC_MODE_METADATA;
+
+        /*
+         * Cannot use preallocation with backing files, but giving a
+         * backing file when specifying data_file_raw is an error
+         * anyway.
+         */
+        assert(!qcow2_opts->has_backing_file);
+    }
 
     if (qcow2_opts->data_file) {
         if (version < 3) {
@@ -4237,6 +4260,18 @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset,
             error_setg_errno(errp, -ret, "Failed to grow the L1 table");
             goto fail;
         }
+
+        if (data_file_is_raw(bs) && prealloc == PREALLOC_MODE_OFF) {
+            /*
+             * When creating a qcow2 image with data-file-raw, we enforce
+             * at least prealloc=metadata, so that the L1/L2 tables are
+             * fully allocated and reading from the data file will return
+             * the same data as reading from the qcow2 image.  When the
+             * image is grown, we must consequently preallocate the
+             * metadata structures to cover the added area.
+             */
+            prealloc = PREALLOC_MODE_METADATA;
+        }
     }
 
     switch (prealloc) {
diff --git a/docs/tools/qemu-storage-daemon.rst b/docs/tools/qemu-storage-daemon.rst
index 086493ebb3..3ec4bdd914 100644
--- a/docs/tools/qemu-storage-daemon.rst
+++ b/docs/tools/qemu-storage-daemon.rst
@@ -74,6 +74,7 @@ Standard options:
 .. option:: --export [type=]nbd,id=<id>,node-name=<node-name>[,name=<export-name>][,writable=on|off][,bitmap=<name>]
   --export [type=]vhost-user-blk,id=<id>,node-name=<node-name>,addr.type=unix,addr.path=<socket-path>[,writable=on|off][,logical-block-size=<block-size>][,num-queues=<num-queues>]
   --export [type=]vhost-user-blk,id=<id>,node-name=<node-name>,addr.type=fd,addr.str=<fd>[,writable=on|off][,logical-block-size=<block-size>][,num-queues=<num-queues>]
+  --export [type=]fuse,id=<id>,node-name=<node-name>,mountpoint=<file>[,growable=on|off][,writable=on|off]
 
   is a block export definition. ``node-name`` is the block node that should be
   exported. ``writable`` determines whether or not the export allows write
@@ -92,6 +93,16 @@ Standard options:
   ``logical-block-size`` sets the logical block size in bytes (the default is
   512). ``num-queues`` sets the number of virtqueues (the default is 1).
 
+  The ``fuse`` export type takes a mount point, which must be a regular file,
+  on which to export the given block node. That file will not be changed, it
+  will just appear to have the block node's content while the export is active
+  (very much like mounting a filesystem on a directory does not change what the
+  directory contains, it only shows a different content while the filesystem is
+  mounted). Consequently, applications that have opened the given file before
+  the export became active will continue to see its original content. If
+  ``growable`` is set, writes after the end of the exported file will grow the
+  block node to fit.
+
 .. option:: --monitor MONITORDEF
 
   is a QMP monitor definition. See the :manpage:`qemu(1)` manual page for
@@ -196,6 +207,14 @@ domain socket ``vhost-user-blk.sock``::
       --blockdev driver=qcow2,node-name=qcow2,file=file \
       --export type=vhost-user-blk,id=export,addr.type=unix,addr.path=vhost-user-blk.sock,node-name=qcow2
 
+Export a qcow2 image file ``disk.qcow2`` via FUSE on itself, so the disk image
+file will then appear as a raw image::
+
+  $ qemu-storage-daemon \
+      --blockdev driver=file,node-name=file,filename=disk.qcow2 \
+      --blockdev driver=qcow2,node-name=qcow2,file=file \
+      --export type=fuse,id=export,node-name=qcow2,mountpoint=disk.qcow2,writable=on
+
 See also
 --------
 
diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c
index 72900dc2ec..fc8b150629 100644
--- a/storage-daemon/qemu-storage-daemon.c
+++ b/storage-daemon/qemu-storage-daemon.c
@@ -98,6 +98,10 @@ static void help(void)
 "                         export the specified block node over NBD\n"
 "                         (requires --nbd-server)\n"
 "\n"
+"  --export [type=]fuse,id=<id>,node-name=<node-name>,mountpoint=<file>\n"
+"           [,growable=on|off][,writable=on|off]\n"
+"                         export the specified block node over FUSE\n"
+"\n"
 "  --monitor [chardev=]name[,mode=control][,pretty[=on|off]]\n"
 "                         configure a QMP monitor\n"
 "\n"
diff --git a/tests/qemu-iotests/046 b/tests/qemu-iotests/046
index 50b0678f60..517b162508 100755
--- a/tests/qemu-iotests/046
+++ b/tests/qemu-iotests/046
@@ -187,7 +187,8 @@ EOF
 }
 
 overlay_io | $QEMU_IO blkdebug::"$TEST_IMG" | _filter_qemu_io |\
-	sed -e 's/bytes at offset [0-9]*/bytes at offset XXX/g'
+    sed -e 's/[0-9]*\/[0-9]* bytes at offset [0-9]*/XXX\/XXX bytes at offset XXX/g' \
+        -e 's/^[0-9]* KiB/XXX KiB/g'
 
 echo
 echo "== Verify image content =="
diff --git a/tests/qemu-iotests/046.out b/tests/qemu-iotests/046.out
index 66ad987ab3..b1a03f4041 100644
--- a/tests/qemu-iotests/046.out
+++ b/tests/qemu-iotests/046.out
@@ -71,74 +71,74 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=6442450944 backing_file=TEST_DIR
 == Some concurrent requests touching the same cluster ==
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 65536/65536 bytes at offset XXX
-64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 65536/65536 bytes at offset XXX
-64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 32768/32768 bytes at offset XXX
-32 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 57344/57344 bytes at offset XXX
-56 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 4096/4096 bytes at offset XXX
-4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 32768/32768 bytes at offset XXX
-32 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-discard 65536/65536 bytes at offset XXX
-64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+discard XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 57344/57344 bytes at offset XXX
-56 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 4096/4096 bytes at offset XXX
-4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 65536/65536 bytes at offset XXX
-64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-discard 65536/65536 bytes at offset XXX
-64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+discard XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 57344/57344 bytes at offset XXX
-56 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 98304/98304 bytes at offset XXX
-96 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 8192/8192 bytes at offset XXX
-8 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 81920/81920 bytes at offset XXX
-80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 blkdebug: Suspended request 'A'
 blkdebug: Resuming request 'A'
-wrote 32768/32768 bytes at offset XXX
-32 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote 98304/98304 bytes at offset XXX
-96 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote XXX/XXX bytes at offset XXX
+XXX KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 == Verify image content ==
 read 65536/65536 bytes at offset 0
diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051
index 333cc81818..7bf29343d7 100755
--- a/tests/qemu-iotests/051
+++ b/tests/qemu-iotests/051
@@ -199,7 +199,7 @@ case "$QEMU_DEFAULT_MACHINE" in
         # virtio-blk enables the iothread only when the driver initialises the
         # device, so a second virtio-blk device can't be added even with the
         # same iothread. virtio-scsi allows this.
-        run_qemu $iothread -device virtio-blk-pci,drive=disk,iohtread=iothread0,share-rw=on
+        run_qemu $iothread -device virtio-blk-pci,drive=disk,iothread=iothread0,share-rw=on
         run_qemu $iothread -device virtio-scsi,id=virtio-scsi1,iothread=thread0 -device scsi-hd,bus=virtio-scsi1.0,drive=disk,share-rw=on
         ;;
      *)
diff --git a/tests/qemu-iotests/051.out b/tests/qemu-iotests/051.out
index 437053c839..441f83e41a 100644
--- a/tests/qemu-iotests/051.out
+++ b/tests/qemu-iotests/051.out
@@ -61,13 +61,13 @@ QEMU X.Y.Z monitor - type 'help' for more information
 (qemu) quit
 
 Testing: -drive file=TEST_DIR/t.qcow2,node-name=123foo
-QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=123foo: Invalid node name
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=123foo: Invalid node-name: '123foo'
 
 Testing: -drive file=TEST_DIR/t.qcow2,node-name=_foo
-QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=_foo: Invalid node name
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=_foo: Invalid node-name: '_foo'
 
 Testing: -drive file=TEST_DIR/t.qcow2,node-name=foo#12
-QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=foo#12: Invalid node name
+QEMU_PROG: -drive file=TEST_DIR/t.qcow2,node-name=foo#12: Invalid node-name: 'foo#12'
 
 
 === Device without drive ===
diff --git a/tests/qemu-iotests/051.pc.out b/tests/qemu-iotests/051.pc.out
index e95bd42b8d..afe7632964 100644
--- a/tests/qemu-iotests/051.pc.out
+++ b/tests/qemu-iotests/051.pc.out
@@ -183,9 +183,9 @@ Testing: -drive file=TEST_DIR/t.qcow2,if=none,node-name=disk -object iothread,id
 QEMU X.Y.Z monitor - type 'help' for more information
 (qemu) QEMU_PROG: -device scsi-hd,bus=virtio-scsi1.0,drive=disk,share-rw=on: Cannot change iothread of active block backend
 
-Testing: -drive file=TEST_DIR/t.qcow2,if=none,node-name=disk -object iothread,id=thread0 -device virtio-scsi,iothread=thread0,id=virtio-scsi0 -device scsi-hd,bus=virtio-scsi0.0,drive=disk,share-rw=on -device virtio-blk-pci,drive=disk,iohtread=iothread0,share-rw=on
+Testing: -drive file=TEST_DIR/t.qcow2,if=none,node-name=disk -object iothread,id=thread0 -device virtio-scsi,iothread=thread0,id=virtio-scsi0 -device scsi-hd,bus=virtio-scsi0.0,drive=disk,share-rw=on -device virtio-blk-pci,drive=disk,iothread=iothread0,share-rw=on
 QEMU X.Y.Z monitor - type 'help' for more information
-(qemu) QEMU_PROG: -device virtio-blk-pci,drive=disk,iohtread=iothread0,share-rw=on: Cannot change iothread of active block backend
+(qemu) QEMU_PROG: -device virtio-blk-pci,drive=disk,iothread=iothread0,share-rw=on: Cannot change iothread of active block backend
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=none,node-name=disk -object iothread,id=thread0 -device virtio-scsi,iothread=thread0,id=virtio-scsi0 -device scsi-hd,bus=virtio-scsi0.0,drive=disk,share-rw=on -device virtio-scsi,id=virtio-scsi1,iothread=thread0 -device scsi-hd,bus=virtio-scsi1.0,drive=disk,share-rw=on
 QEMU X.Y.Z monitor - type 'help' for more information
diff --git a/tests/qemu-iotests/116.out b/tests/qemu-iotests/116.out
index 49f9a261a0..5f6c6fffca 100644
--- a/tests/qemu-iotests/116.out
+++ b/tests/qemu-iotests/116.out
@@ -2,7 +2,7 @@ QA output created by 116
 
 == truncated header cluster ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-qemu-io: can't open device TEST_DIR/t.qed: Could not open 'TEST_DIR/t.qed': Invalid argument
+qemu-io: can't open device TEST_DIR/t.qed: QED table offset is invalid
 
 == invalid header magic ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
@@ -10,21 +10,21 @@ qemu-io: can't open device TEST_DIR/t.qed: Image not in QED format
 
 == invalid cluster size ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-qemu-io: can't open device TEST_DIR/t.qed: Could not open 'TEST_DIR/t.qed': Invalid argument
+qemu-io: can't open device TEST_DIR/t.qed: QED cluster size is invalid
 
 == invalid table size ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-qemu-io: can't open device TEST_DIR/t.qed: Could not open 'TEST_DIR/t.qed': Invalid argument
+qemu-io: can't open device TEST_DIR/t.qed: QED table size is invalid
 
 == invalid header size ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-qemu-io: can't open device TEST_DIR/t.qed: Could not open 'TEST_DIR/t.qed': Invalid argument
+qemu-io: can't open device TEST_DIR/t.qed: QED table offset is invalid
 
 == invalid L1 table offset ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-qemu-io: can't open device TEST_DIR/t.qed: Could not open 'TEST_DIR/t.qed': Invalid argument
+qemu-io: can't open device TEST_DIR/t.qed: QED table offset is invalid
 
 == invalid image size ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-qemu-io: can't open device TEST_DIR/t.qed: Could not open 'TEST_DIR/t.qed': Invalid argument
+qemu-io: can't open device TEST_DIR/t.qed: QED image size is invalid
 *** done
diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244
index a46b441627..3e61fa25bb 100755
--- a/tests/qemu-iotests/244
+++ b/tests/qemu-iotests/244
@@ -38,6 +38,7 @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # get standard environment, filters and checks
 . ./common.rc
 . ./common.filter
+. ./common.qemu
 
 _supported_fmt qcow2
 _supported_proto file
@@ -267,6 +268,109 @@ case $result in
         ;;
 esac
 
+echo
+echo '=== Preallocation with data-file-raw ==='
+
+echo
+echo '--- Using a non-zeroed data file ---'
+
+# Using data-file-raw must enforce at least metadata preallocation so
+# that it does not matter whether one reads the raw file or the qcow2
+# file
+
+# Pre-create the data file, write some data.  Real-world use cases for
+# this are adding a qcow2 metadata file to a block device (i.e., using
+# the device as the data file) or adding qcow2 features to pre-existing
+# raw images (e.g. because the user now wants persistent dirty bitmaps).
+truncate -s 1M "$TEST_IMG.data"
+$QEMU_IO -f raw -c 'write -P 42 0 1M' "$TEST_IMG.data" | _filter_qemu_io
+
+# We cannot use qemu-img to create the qcow2 image, because it would
+# clear the data file.  Use the blockdev-create job instead, which will
+# only format the qcow2 image file.
+touch "$TEST_IMG"
+_launch_qemu \
+    -blockdev file,node-name=data,filename="$TEST_IMG.data" \
+    -blockdev file,node-name=meta,filename="$TEST_IMG"
+
+_send_qemu_cmd $QEMU_HANDLE '{ "execute": "qmp_capabilities" }' 'return'
+
+_send_qemu_cmd $QEMU_HANDLE \
+    '{ "execute": "blockdev-create",
+       "arguments": {
+           "job-id": "create",
+           "options": {
+               "driver": "qcow2",
+               "size": '"$((1 * 1024 * 1024))"',
+               "file": "meta",
+               "data-file": "data",
+               "data-file-raw": true
+           } } }' \
+    '"status": "concluded"'
+
+_send_qemu_cmd $QEMU_HANDLE \
+    '{ "execute": "job-dismiss", "arguments": { "id": "create" } }' \
+    'return'
+
+_cleanup_qemu
+
+echo
+echo 'Comparing pattern:'
+
+# Reading from either the qcow2 file or the data file should return
+# the same result:
+$QEMU_IO -f raw -c 'read -P 42 0 1M' "$TEST_IMG.data" | _filter_qemu_io
+$QEMU_IO -f $IMGFMT -c 'read -P 42 0 1M' "$TEST_IMG" | _filter_qemu_io
+
+# For good measure
+$QEMU_IMG compare -f raw "$TEST_IMG.data" "$TEST_IMG"
+
+echo
+echo '--- Truncation (growing) ---'
+
+# Append some new data to the raw file, then resize the qcow2 image
+# accordingly and see whether the new data is visible.  Technically
+# that is not allowed, but it is reasonable behavior, so test it.
+truncate -s 2M "$TEST_IMG.data"
+$QEMU_IO -f raw -c 'write -P 84 1M 1M' "$TEST_IMG.data" | _filter_qemu_io
+
+$QEMU_IMG resize "$TEST_IMG" 2M
+
+echo
+echo 'Comparing pattern:'
+
+$QEMU_IO -f raw -c 'read -P 42 0 1M' -c 'read -P 84 1M 1M' "$TEST_IMG.data" \
+    | _filter_qemu_io
+$QEMU_IO -f $IMGFMT -c 'read -P 42 0 1M' -c 'read -P 84 1M 1M' "$TEST_IMG" \
+    | _filter_qemu_io
+
+$QEMU_IMG compare -f raw "$TEST_IMG.data" "$TEST_IMG"
+
+echo
+echo '--- Giving a backing file at runtime ---'
+
+# qcow2 files with data-file-raw cannot have backing files given by
+# their image header, but qemu will allow you to set a backing node at
+# runtime -- it should not have any effect, though (because reading
+# from the qcow2 node should return the same data as reading from the
+# raw node).
+
+_make_test_img -o "data_file=$TEST_IMG.data,data_file_raw=on" 1M
+TEST_IMG="$TEST_IMG.base" _make_test_img 1M
+
+# Write something that is not zero into the base image
+$QEMU_IO -c 'write -P 42 0 1M' "$TEST_IMG.base" | _filter_qemu_io
+
+echo
+echo 'Comparing qcow2 image and raw data file:'
+
+# $TEST_IMG and $TEST_IMG.data must show the same data at all times;
+# that is, the qcow2 node must not fall through to the backing image
+# at any point
+$QEMU_IMG compare --image-opts \
+    "driver=raw,file.filename=$TEST_IMG.data"  \
+    "file.filename=$TEST_IMG,backing.file.filename=$TEST_IMG.base"
+
 # success, all done
 echo "*** done"
 rm -f $seq.full
diff --git a/tests/qemu-iotests/244.out b/tests/qemu-iotests/244.out
index 7269b4295a..99f56ac18c 100644
--- a/tests/qemu-iotests/244.out
+++ b/tests/qemu-iotests/244.out
@@ -83,7 +83,7 @@ qcow2 file size after I/O: 327680
 === Standalone image with external data file (valid raw) ===
 
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 data_file=TEST_DIR/t.IMGFMT.data data_file_raw=on
-qcow2 file size before I/O: 196616
+qcow2 file size before I/O: 327680
 
 wrote 4194304/4194304 bytes at offset 1048576
 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -93,11 +93,10 @@ wrote 3145728/3145728 bytes at offset 3145728
 3 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 No errors were found on the image.
 
-[{ "start": 0, "length": 1048576, "depth": 0, "zero": true, "data": false},
-{ "start": 1048576, "length": 1048576, "depth": 0, "zero": false, "data": true, "offset": 1048576},
+[{ "start": 0, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": 0},
 { "start": 2097152, "length": 2097152, "depth": 0, "zero": true, "data": false},
-{ "start": 4194304, "length": 1048576, "depth": 0, "zero": true, "data": false, "offset": 4194304},
-{ "start": 5242880, "length": 61865984, "depth": 0, "zero": true, "data": false}]
+{ "start": 4194304, "length": 2097152, "depth": 0, "zero": true, "data": false, "offset": 4194304},
+{ "start": 6291456, "length": 60817408, "depth": 0, "zero": false, "data": true, "offset": 6291456}]
 
 read 1048576/1048576 bytes at offset 0
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -138,4 +137,63 @@ wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 Success: qemu-io failed, so the data file was flushed
+
+=== Preallocation with data-file-raw ===
+
+--- Using a non-zeroed data file ---
+wrote 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+{ "execute": "qmp_capabilities" }
+{"return": {}}
+{ "execute": "blockdev-create",
+       "arguments": {
+           "job-id": "create",
+           "options": {
+               "driver": "IMGFMT",
+               "size": 1048576,
+               "file": "meta",
+               "data-file": "data",
+               "data-file-raw": true
+           } } }
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "create"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "create"}}
+{"return": {}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "create"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "create"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "create"}}
+{ "execute": "job-dismiss", "arguments": { "id": "create" } }
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "create"}}
+{"return": {}}
+
+Comparing pattern:
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Images are identical.
+
+--- Truncation (growing) ---
+wrote 1048576/1048576 bytes at offset 1048576
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image resized.
+
+Comparing pattern:
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 1048576/1048576 bytes at offset 1048576
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 1048576/1048576 bytes at offset 1048576
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Images are identical.
+
+--- Giving a backing file at runtime ---
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 data_file=TEST_DIR/t.IMGFMT.data data_file_raw=on
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=1048576
+wrote 1048576/1048576 bytes at offset 0
+1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+Comparing qcow2 image and raw data file:
+Images are identical.
 *** done