Series comparison

The following changes since commit eb6490f544388dd24c0d054a96dd304bc7284450:

Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200703' into staging (2020-07-04 16:08:41 +0100)

are available in the Git repository at:

https://github.com/XanClic/qemu.git tags/pull-block-2020-07-06

for you to fetch changes up to 365fed5111b06d31c1632af63c7528dfe49d62a2:

qed: Simplify backing reads (2020-07-06 10:34:14 +0200)

----------------------------------------------------------------
Block patches for 5.1:
- LUKS keyslot amendment
  (+ patches to make the iotests pass on non-Linux systems, and to keep
     the tests passing for qcow v1, and to skip LUKS tests (including
     qcow2 LUKS) when the built qemu does not support it)
- Refactoring in the block layer: Drop the basically unnecessary
  unallocated_blocks_are_zero field from BlockDriverInfo
- Fix qcow2 preallocation when the image size is not a multiple of the
  cluster size
- Fix in block-copy code

----------------------------------------------------------------
Alberto Garcia (1):
  qcow2: Fix preallocation on images with unaligned sizes

Eric Blake (1):
  qed: Simplify backing reads

Max Reitz (5):
  iotests: Make _filter_img_create more active
  iotests/common.rc: Add _require_working_luks
  iotests.py: Add qemu_img_pipe_and_status()
  iotests.py: Add (verify|has)_working_luks()
  iotests: Check whether luks works

Maxim Levitsky (14):
  iotests: filter few more luks specific create options
  qcrypto/core: add generic infrastructure for crypto options amendment
  qcrypto/luks: implement encryption key management
  block/amend: add 'force' option
  block/amend: separate amend and create options for qemu-img
  block/amend: refactor qcow2 amend options
  block/crypto: rename two functions
  block/crypto: implement the encryption key management
  block/qcow2: extend qemu-img amend interface with crypto options
  iotests: qemu-img tests for luks key management
  block/core: add generic infrastructure for x-blockdev-amend qmp
    command
  block/crypto: implement blockdev-amend
  block/qcow2: implement blockdev-amend
  iotests: add tests for blockdev-amend

Vladimir Sementsov-Ogievskiy (10):
  block/block-copy: block_copy_dirty_clusters: fix failure check
  qemu-img: convert: don't use unallocated_blocks_are_zero
  block: inline bdrv_unallocated_blocks_are_zero()
  block/vdi: return ZERO block-status when appropriate
  block/vpc: return ZERO block-status when appropriate
  block/crypto: drop unallocated_blocks_are_zero
  block/iscsi: drop unallocated_blocks_are_zero
  block/file-posix: drop unallocated_blocks_are_zero
  block/vhdx: drop unallocated_blocks_are_zero
  block: drop unallocated_blocks_are_zero

-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

ret may be > 0 on success path at this point. Fix assertion, which may
crash currently.

Fixes: 4ce5dd3e9b5ee0fac18625860eb3727399ee965e
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20200526181347.489557-1-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/block-copy.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/block/block-copy.c b/block/block-copy.c
index XXXXXXX..XXXXXXX 100644
--- a/block/block-copy.c
+++ b/block/block-copy.c
@@ -XXX,XX +XXX,XX @@ out:
          * block_copy_task_run. If it fails, it means some task already failed
          * for real reason, let's return first failure.
          * Still, assert that we don't rewrite failure by success.
+         *
+         * Note: ret may be positive here because of block-status result.
          */
-        assert(ret == 0 || aio_task_pool_status(aio) < 0);
+        assert(ret >= 0 || aio_task_pool_status(aio) < 0);
         ret = aio_task_pool_status(aio);
 
         aio_task_pool_free(aio);
-- 
2.26.2

From: Alberto Garcia <berto@igalia.com>

When resizing an image with qcow2_co_truncate() using the falloc or
full preallocation modes the code assumes that both the old and new
sizes are cluster-aligned.

There are two problems with this:

1) The calculation of how many clusters are involved does not always
     get the right result.

Example: creating a 60KB image and resizing it (with
     preallocation=full) to 80KB won't allocate the second cluster.

2) No copy-on-write is performed, so in the previous example if
     there is a backing file then the first 60KB of the first cluster
     won't be filled with data from the backing file.

This patch fixes both issues.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Message-Id: <20200617140036.20311-1-berto@igalia.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/qcow2.c              | 17 ++++++++++++++---
 tests/qemu-iotests/125     | 24 ++++++++++++++++++++++++
 tests/qemu-iotests/125.out |  9 +++++++++
 3 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset,
             old_file_size = ROUND_UP(old_file_size, s->cluster_size);
         }
 
-        nb_new_data_clusters = DIV_ROUND_UP(offset - old_length,
-                                            s->cluster_size);
+        nb_new_data_clusters = (ROUND_UP(offset, s->cluster_size) -
+            start_of_cluster(s, old_length)) >> s->cluster_bits;
 
         /* This is an overestimation; we will not actually allocate space for
          * these in the file but just make sure the new refcount structures are
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset,
             int64_t nb_clusters = MIN(
                 nb_new_data_clusters,
                 s->l2_slice_size - offset_to_l2_slice_index(s, guest_offset));
-            QCowL2Meta allocation = {
+            unsigned cow_start_length = offset_into_cluster(s, guest_offset);
+            QCowL2Meta allocation;
+            guest_offset = start_of_cluster(s, guest_offset);
+            allocation = (QCowL2Meta) {
                 .offset       = guest_offset,
                 .alloc_offset = host_offset,
                 .nb_clusters  = nb_clusters,
+                .cow_start    = {
+                    .offset       = 0,
+                    .nb_bytes     = cow_start_length,
+                },
+                .cow_end      = {
+                    .offset       = nb_clusters << s->cluster_bits,
+                    .nb_bytes     = 0,
+                },
             };
             qemu_co_queue_init(&allocation.dependent_requests);
 
diff --git a/tests/qemu-iotests/125 b/tests/qemu-iotests/125
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/125
+++ b/tests/qemu-iotests/125
@@ -XXX,XX +XXX,XX @@ for GROWTH_SIZE in 16 48 80; do
 done
 done
 
+# Test image resizing using preallocation and unaligned offsets
+$QEMU_IMG create -f raw "$TEST_IMG.base" 128k | _filter_img_create
+$QEMU_IO -c 'write -q -P 1 0 128k' -f raw "$TEST_IMG.base"
+for orig_size in 31k 33k; do
+    echo "--- Resizing image from $orig_size to 96k ---"
+    _make_test_img -F raw -b "$TEST_IMG.base" -o cluster_size=64k "$orig_size"
+    $QEMU_IMG resize -f "$IMGFMT" --preallocation=full "$TEST_IMG" 96k
+    # The first part of the image should contain data from the backing file
+    $QEMU_IO -c "read -q -P 1 0 ${orig_size}" "$TEST_IMG"
+    # The resized part of the image should contain zeroes
+    $QEMU_IO -c "read -q -P 0 ${orig_size} 63k" "$TEST_IMG"
+    # If the image does not have an external data file we can also verify its
+    # actual size. The resized image should have 7 clusters:
+    # header, L1 table, L2 table, refcount table, refcount block, 2 data clusters
+    if ! _get_data_file "$TEST_IMG" > /dev/null; then
+        expected_file_length=$((65536 * 7))
+        file_length=$(stat -c '%s' "$TEST_IMG_FILE")
+        if [ "$file_length" != "$expected_file_length" ]; then
+            echo "ERROR: file length $file_length (expected $expected_file_length)"
+        fi
+    fi
+    echo
+done
+
 # success, all done
 echo '*** done'
 rm -f $seq.full
diff --git a/tests/qemu-iotests/125.out b/tests/qemu-iotests/125.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/125.out
+++ b/tests/qemu-iotests/125.out
@@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0
 wrote 81920/81920 bytes at offset 2048000
 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=raw size=131072
+--- Resizing image from 31k to 96k ---
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=31744 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=raw
+Image resized.
+
+--- Resizing image from 33k to 96k ---
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33792 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=raw
+Image resized.
+
 *** done
-- 
2.26.2

Right now, _filter_img_create just filters out everything that looks
format-dependent, and applies some filename filters.  That means that we
have to add another filter line every time some format gets a new
creation option.  This can be avoided by instead discarding everything
and just keeping what we know is format-independent (format, size,
backing file, encryption information[1], preallocation) or just
interesting to have in the reference output (external data file path).

Furthermore, we probably want to sort these options.  Format drivers are
not required to define them in any specific order, so the output is
effectively random (although this has never bothered us until now).  We
need a specific order for our reference outputs, though.  Unfortunately,
just using a plain "sort" would change a lot of existing reference
outputs, so we have to pre-filter the option keys to keep our existing
order (fmt, size, backing*, data, encryption info, preallocation).

Finally, this makes it difficult for _filter_img_create to automagically
work for QMP output.  Thus, this patch adds a separate
_filter_img_create_for_qmp function that echos every line verbatim that
does not start with "Formatting", and pipes those "Formatting" lines to
_filter_img_create.

[1] Actually, the only thing that is really important is whether
    encryption is enabled or not.  A patch by Maxim thus removes all
    other "encrypt.*" options from the output:
    https://lists.nongnu.org/archive/html/qemu-block/2020-06/msg00339.html
    But that patch needs to come later so we can get away with changing
    as few reference outputs in this patch here as possible.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-2-mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 tests/qemu-iotests/112.out       |   2 +-
 tests/qemu-iotests/141           |   2 +-
 tests/qemu-iotests/153           |   9 ++-
 tests/qemu-iotests/common.filter | 109 ++++++++++++++++++++++++-------
 4 files changed, 91 insertions(+), 31 deletions(-)

diff --git a/tests/qemu-iotests/112.out b/tests/qemu-iotests/112.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/112.out
+++ b/tests/qemu-iotests/112.out
@@ -XXX,XX +XXX,XX @@ QA output created by 112
 qemu-img: TEST_DIR/t.IMGFMT: Refcount width must be a power of two and may not exceed 64 bits
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
 qemu-img: TEST_DIR/t.IMGFMT: Refcount width must be a power of two and may not exceed 64 bits
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 refcount_bits=-1
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
 qemu-img: TEST_DIR/t.IMGFMT: Refcount width must be a power of two and may not exceed 64 bits
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
 qemu-img: TEST_DIR/t.IMGFMT: Refcount width must be a power of two and may not exceed 64 bits
diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/141
+++ b/tests/qemu-iotests/141
@@ -XXX,XX +XXX,XX @@ test_blockjob()
     _send_qemu_cmd $QEMU_HANDLE \
         "$1" \
         "$2" \
-        | _filter_img_create | _filter_qmp_empty_return
+        | _filter_img_create_in_qmp | _filter_qmp_empty_return
 
     # We want this to return an error because the block job is still running
     _send_qemu_cmd $QEMU_HANDLE \
diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/153
+++ b/tests/qemu-iotests/153
@@ -XXX,XX +XXX,XX @@ done
 
 echo
 echo "== Creating ${TEST_IMG}.[abc] ==" | _filter_testdir
-(
-    $QEMU_IMG create -f qcow2 "${TEST_IMG}.a" -b "${TEST_IMG}"
-    $QEMU_IMG create -f qcow2 "${TEST_IMG}.b" -b "${TEST_IMG}"
-    $QEMU_IMG create -f qcow2 "${TEST_IMG}.c" -b "${TEST_IMG}.b"
-) | _filter_img_create
+$QEMU_IMG create -f qcow2 "${TEST_IMG}.a" -b "${TEST_IMG}" | _filter_img_create
+$QEMU_IMG create -f qcow2 "${TEST_IMG}.b" -b "${TEST_IMG}" | _filter_img_create
+$QEMU_IMG create -f qcow2 "${TEST_IMG}.c" -b "${TEST_IMG}.b" \
+    | _filter_img_create
 
 echo
 echo "== Two devices sharing the same file in backing chain =="
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -XXX,XX +XXX,XX @@ _filter_actual_image_size()
 # replace driver-specific options in the "Formatting..." line
 _filter_img_create()
 {
-    data_file_filter=()
-    if data_file=$(_get_data_file "$TEST_IMG"); then
-        data_file_filter=(-e "s# data_file=$data_file##")
+    # Split the line into the pre-options part ($filename_part, which
+    # precedes ", fmt=") and the options part ($options, which starts
+    # with "fmt=")
+    # (And just echo everything before the first "^Formatting")
+    readarray formatting_line < <($SED -e 's/, fmt=/\n/')
+
+    filename_part=''
+    options=''
+    lines=${#formatting_line[@]}
+    for ((i = 0; i < $lines; i++)); do
+        line=${formatting_line[i]}
+        unset formatting_line[i]
+
+        filename_part="$filename_part$line"
+
+        if echo "$line" | grep -q '^Formatting'; then
+            next_i=$((i + 1))
+            if [ -n "${formatting_line[next_i]}" ]; then
+                options="fmt=${formatting_line[@]}"
+            fi
+            break
+        fi
+    done
+
+    # Set grep_data_file to '\|data_file' to keep it; make it empty
+    # to drop it.
+    # We want to drop it if it is part of the global $IMGOPTS, and we
+    # want to keep it otherwise (if the test specifically wants to
+    # test data files).
+    grep_data_file=(-e data_file)
+    if _get_data_file "$TEST_IMG" > /dev/null; then
+        grep_data_file=()
     fi
 
-    $SED "${data_file_filter[@]}" \
+    filename_filters=(
         -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \
         -e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \
         -e "s#$TEST_DIR#TEST_DIR#g" \
         -e "s#$SOCK_DIR#SOCK_DIR#g" \
         -e "s#$IMGFMT#IMGFMT#g" \
         -e 's#nbd:127.0.0.1:[0-9]\\+#TEST_DIR/t.IMGFMT#g' \
-        -e 's#nbd+unix:///\??socket=SOCK_DIR/nbd#TEST_DIR/t.IMGFMT#g' \
-        -e "s# encryption=off##g" \
-        -e "s# cluster_size=[0-9]\\+##g" \
-        -e "s# table_size=[0-9]\\+##g" \
-        -e "s# compat=[^ ]*##g" \
-        -e "s# compat6=\$on\\|off\$##g" \
-        -e "s# static=\$on\\|off\$##g" \
-        -e "s# zeroed_grain=\$on\\|off\$##g" \
-        -e "s# subformat=[^ ]*##g" \
-        -e "s# adapter_type=[^ ]*##g" \
-        -e "s# hwversion=[^ ]*##g" \
-        -e "s# lazy_refcounts=\$on\\|off\$##g" \
-        -e "s# block_size=[0-9]\\+##g" \
-        -e "s# block_state_zero=\$on\\|off\$##g" \
-        -e "s# log_size=[0-9]\\+##g" \
-        -e "s# refcount_bits=[0-9]\\+##g" \
-        -e "s# key-secret=[a-zA-Z0-9]\\+##g" \
-        -e "s# iter-time=[0-9]\\+##g" \
-        -e "s# force_size=\$on\\|off\$##g" \
-        -e "s# compression_type=[a-zA-Z0-9]\\+##g"
+        -e 's#nbd+unix:///\??socket=SOCK_DIR/nbd#TEST_DIR/t.IMGFMT#g'
+    )
+
+    filename_part=$(echo "$filename_part" | $SED "${filename_filters[@]}")
+
+    # Break the option line before each option (preserving pre-existing
+    # line breaks by replacing them by \0 and restoring them at the end),
+    # then filter out the options we want to keep and sort them according
+    # to some order that all block drivers used at the time of writing
+    # this function.
+    options=$(
+        echo "$options" \
+        | tr '\n' '\0' \
+        | $SED -e 's/ $[a-z0-9_.-]*$=/\n\1=/g' \
+        | grep -a -e '^fmt' -e '^size' -e '^backing' -e '^preallocation' \
+                  -e '^encrypt' "${grep_data_file[@]}" \
+        | $SED "${filename_filters[@]}" \
+            -e 's/^$fmt$/0-\1/' \
+            -e 's/^$size$/1-\1/' \
+            -e 's/^$backing$/2-\1/' \
+            -e 's/^$data_file$/3-\1/' \
+            -e 's/^$encryption$/4-\1/' \
+            -e 's/^$encrypt\.format$/5-\1/' \
+            -e 's/^$encrypt\.key-secret$/6-\1/' \
+            -e 's/^$encrypt\.iter-time$/7-\1/' \
+            -e 's/^$preallocation$/8-\1/' \
+        | sort \
+        | $SED -e 's/^[0-9]-//' \
+        | tr '\n\0' ' \n' \
+        | $SED -e 's/^ *$//' -e 's/ *$//'
+    )
+
+    if [ -n "$options" ]; then
+        echo "$filename_part, $options"
+    elif [ -n "$filename_part" ]; then
+        echo "$filename_part"
+    fi
+}
+
+# Filter the "Formatting..." line in QMP output (leaving the QMP output
+# untouched)
+# (In contrast to _filter_img_create(), this function does not support
+# multi-line Formatting output)
+_filter_img_create_in_qmp()
+{
+    while read -r line; do
+        if echo "$line" | grep -q '^Formatting'; then
+            echo "$line" | _filter_img_create
+        else
+            echo "$line"
+        fi
+    done
 }
 
 _filter_img_create_size()
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

This allows more tests to be able to have same output on both qcow2 luks encrypted images
and raw luks images

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200625125548.870061-3-mreitz@redhat.com>
---
 tests/qemu-iotests/087.out       | 6 +++---
 tests/qemu-iotests/134.out       | 2 +-
 tests/qemu-iotests/158.out       | 4 ++--
 tests/qemu-iotests/188.out       | 2 +-
 tests/qemu-iotests/189.out       | 4 ++--
 tests/qemu-iotests/198.out       | 4 ++--
 tests/qemu-iotests/263.out       | 4 ++--
 tests/qemu-iotests/284.out       | 6 +++---
 tests/qemu-iotests/common.filter | 5 +----
 9 files changed, 17 insertions(+), 20 deletions(-)

diff --git a/tests/qemu-iotests/087.out b/tests/qemu-iotests/087.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/087.out
+++ b/tests/qemu-iotests/087.out
@@ -XXX,XX +XXX,XX @@ QMP_VERSION
 
 === Encrypted image QCow ===
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on
 Testing:
 QMP_VERSION
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ QMP_VERSION
 
 === Encrypted image LUKS ===
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encrypt.format=luks encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 Testing:
 QMP_VERSION
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ QMP_VERSION
 
 === Missing driver ===
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on
 Testing: -S
 QMP_VERSION
 {"return": {}}
diff --git a/tests/qemu-iotests/134.out b/tests/qemu-iotests/134.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/134.out
+++ b/tests/qemu-iotests/134.out
@@ -XXX,XX +XXX,XX @@
 QA output created by 134
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on
 
 == reading whole image ==
 read 134217728/134217728 bytes at offset 0
diff --git a/tests/qemu-iotests/158.out b/tests/qemu-iotests/158.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/158.out
+++ b/tests/qemu-iotests/158.out
@@ -XXX,XX +XXX,XX @@
 QA output created by 158
 == create base ==
-Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728 encryption=on encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728 encryption=on
 
 == writing whole image ==
 wrote 134217728/134217728 bytes at offset 0
@@ -XXX,XX +XXX,XX @@ wrote 134217728/134217728 bytes at offset 0
 read 134217728/134217728 bytes at offset 0
 128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 == create overlay ==
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base encryption=on encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base encryption=on
 
 == writing part of a cluster ==
 wrote 1024/1024 bytes at offset 0
diff --git a/tests/qemu-iotests/188.out b/tests/qemu-iotests/188.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/188.out
+++ b/tests/qemu-iotests/188.out
@@ -XXX,XX +XXX,XX @@
 QA output created by 188
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=16777216 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=16777216
 
 == reading whole image ==
 read 16777216/16777216 bytes at offset 0
diff --git a/tests/qemu-iotests/189.out b/tests/qemu-iotests/189.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/189.out
+++ b/tests/qemu-iotests/189.out
@@ -XXX,XX +XXX,XX @@
 QA output created by 189
 == create base ==
-Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=16777216 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=16777216
 
 == writing whole image ==
 wrote 16777216/16777216 bytes at offset 0
@@ -XXX,XX +XXX,XX @@ wrote 16777216/16777216 bytes at offset 0
 read 16777216/16777216 bytes at offset 0
 16 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 == create overlay ==
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=16777216 backing_file=TEST_DIR/t.IMGFMT.base encrypt.format=luks encrypt.key-secret=sec1 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=16777216 backing_file=TEST_DIR/t.IMGFMT.base
 
 == writing part of a cluster ==
 wrote 1024/1024 bytes at offset 0
diff --git a/tests/qemu-iotests/198.out b/tests/qemu-iotests/198.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/198.out
+++ b/tests/qemu-iotests/198.out
@@ -XXX,XX +XXX,XX @@
 QA output created by 198
 == create base ==
-Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=16777216 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=16777216
 
 == writing whole image base ==
 wrote 16777216/16777216 bytes at offset 0
 16 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 == create overlay ==
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=16777216 backing_file=TEST_DIR/t.IMGFMT.base encrypt.format=luks encrypt.key-secret=sec1 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=16777216 backing_file=TEST_DIR/t.IMGFMT.base
 
 == writing whole image layer ==
 wrote 16777216/16777216 bytes at offset 0
diff --git a/tests/qemu-iotests/263.out b/tests/qemu-iotests/263.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/263.out
+++ b/tests/qemu-iotests/263.out
@@ -XXX,XX +XXX,XX @@ QA output created by 263
 
 testing LUKS qcow2 encryption
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
 == reading the whole image ==
 read 1048576/1048576 bytes at offset 0
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 982528/982528 bytes at offset 66048
 
 testing legacy AES qcow2 encryption
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=aes encrypt.key-secret=sec0
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
 == reading the whole image ==
 read 1048576/1048576 bytes at offset 0
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
diff --git a/tests/qemu-iotests/284.out b/tests/qemu-iotests/284.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/284.out
+++ b/tests/qemu-iotests/284.out
@@ -XXX,XX +XXX,XX @@ QA output created by 284
 
 testing LUKS qcow2 encryption
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
 
 == cluster size 512
 == checking image refcounts ==
@@ -XXX,XX +XXX,XX @@ wrote 1/1 bytes at offset 512
 
 == rechecking image refcounts ==
 No errors were found on the image.
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
 
 == cluster size 2048
 == checking image refcounts ==
@@ -XXX,XX +XXX,XX @@ wrote 1/1 bytes at offset 2048
 
 == rechecking image refcounts ==
 No errors were found on the image.
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
 
 == cluster size 32768
 == checking image refcounts ==
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -XXX,XX +XXX,XX @@ _filter_img_create()
         | tr '\n' '\0' \
         | $SED -e 's/ $[a-z0-9_.-]*$=/\n\1=/g' \
         | grep -a -e '^fmt' -e '^size' -e '^backing' -e '^preallocation' \
-                  -e '^encrypt' "${grep_data_file[@]}" \
+                  -e '^encryption' "${grep_data_file[@]}" \
         | $SED "${filename_filters[@]}" \
             -e 's/^$fmt$/0-\1/' \
             -e 's/^$size$/1-\1/' \
             -e 's/^$backing$/2-\1/' \
             -e 's/^$data_file$/3-\1/' \
             -e 's/^$encryption$/4-\1/' \
-            -e 's/^$encrypt\.format$/5-\1/' \
-            -e 's/^$encrypt\.key-secret$/6-\1/' \
-            -e 's/^$encrypt\.iter-time$/7-\1/' \
             -e 's/^$preallocation$/8-\1/' \
         | sort \
         | $SED -e 's/^[0-9]-//' \
-- 
2.26.2

That the luks driver is present is little indication on whether it is
actually working.  Without the crypto libraries linked in, it does not
work.  So add this function, which tries to create a luks image to see
whether that actually works.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-4-mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 tests/qemu-iotests/common.rc | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -XXX,XX +XXX,XX @@ _unsupported_imgopts()
     done
 }
 
+# Caution: Overwrites $TEST_DIR/t.luks
+_require_working_luks()
+{
+    file="$TEST_DIR/t.luks"
+
+    output=$(
+        $QEMU_IMG create -f luks \
+            --object secret,id=sec0,data=hunter0 \
+            -o key-secret=sec0 \
+            -o iter-time=10 \
+            "$file" \
+            1M \
+            2>&1
+    )
+    status=$?
+
+    IMGFMT='luks' _rm_test_img "$file"
+
+    if [ $status != 0 ]; then
+        reason=$(echo "$output" | grep "$file:" | $SED -e "s#.*$file: *##")
+        if [ -z "$reason" ]; then
+            reason="Failed to create a LUKS image"
+        fi
+        _notrun "$reason"
+    fi
+}
+
 # this test requires that a specified command (executable) exists
 #
 _require_command()
-- 
2.26.2

This function will be used by the next patch, which intends to check
both the exit code and qemu-img's output.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-5-mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
[mreitz: Rebased on 49438972b8c2e]
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/iotests.py | 40 +++++++++++++++++------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -XXX,XX +XXX,XX @@ import struct
 import subprocess
 import sys
 from typing import (Any, Callable, Dict, Iterable,
-                    List, Optional, Sequence, TypeVar)
+                    List, Optional, Sequence, Tuple, TypeVar)
 import unittest
 
 # pylint: disable=import-error, wrong-import-position
@@ -XXX,XX +XXX,XX @@ luks_default_secret_object = 'secret,id=keysec0,data=' + \
 luks_default_key_secret_opt = 'key-secret=keysec0'
 
 
-def qemu_img(*args):
-    '''Run qemu-img and return the exit code'''
-    devnull = open('/dev/null', 'r+')
-    exitcode = subprocess.call(qemu_img_args + list(args),
-                               stdin=devnull, stdout=devnull)
-    if exitcode < 0:
+def qemu_img_pipe_and_status(*args: str) -> Tuple[str, int]:
+    """
+    Run qemu-img and return both its output and its exit code
+    """
+    subp = subprocess.Popen(qemu_img_args + list(args),
+                            stdout=subprocess.PIPE,
+                            stderr=subprocess.STDOUT,
+                            universal_newlines=True)
+    output = subp.communicate()[0]
+    if subp.returncode < 0:
         sys.stderr.write('qemu-img received signal %i: %s\n'
-                         % (-exitcode, ' '.join(qemu_img_args + list(args))))
-    return exitcode
+                         % (-subp.returncode,
+                            ' '.join(qemu_img_args + list(args))))
+    return (output, subp.returncode)
+
+def qemu_img(*args: str) -> int:
+    '''Run qemu-img and return the exit code'''
+    return qemu_img_pipe_and_status(*args)[1]
 
 def ordered_qmp(qmsg, conv_keys=True):
     # Dictionaries are not ordered prior to 3.6, therefore:
@@ -XXX,XX +XXX,XX @@ def qemu_img_verbose(*args):
                          % (-exitcode, ' '.join(qemu_img_args + list(args))))
     return exitcode
 
-def qemu_img_pipe(*args):
+def qemu_img_pipe(*args: str) -> str:
     '''Run qemu-img and return its output'''
-    subp = subprocess.Popen(qemu_img_args + list(args),
-                            stdout=subprocess.PIPE,
-                            stderr=subprocess.STDOUT,
-                            universal_newlines=True)
-    output = subp.communicate()[0]
-    if subp.returncode < 0:
-        sys.stderr.write('qemu-img received signal %i: %s\n'
-                         % (-subp.returncode,
-                            ' '.join(qemu_img_args + list(args))))
-    return output
+    return qemu_img_pipe_and_status(*args)[0]
 
 def qemu_img_log(*args):
     result = qemu_img_pipe(*args)
-- 
2.26.2

Similar to _require_working_luks for bash tests, these functions can be
used to check whether our luks driver can actually create images.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-6-mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 tests/qemu-iotests/iotests.py | 39 +++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -XXX,XX +XXX,XX @@ def verify_quorum():
     if not supports_quorum():
         notrun('quorum support missing')
 
+def has_working_luks() -> Tuple[bool, str]:
+    """
+    Check whether our LUKS driver can actually create images
+    (this extends to LUKS encryption for qcow2).
+
+    If not, return the reason why.
+    """
+
+    img_file = f'{test_dir}/luks-test.luks'
+    (output, status) = \
+        qemu_img_pipe_and_status('create', '-f', 'luks',
+                                 '--object', luks_default_secret_object,
+                                 '-o', luks_default_key_secret_opt,
+                                 '-o', 'iter-time=10',
+                                 img_file, '1G')
+    try:
+        os.remove(img_file)
+    except OSError:
+        pass
+
+    if status != 0:
+        reason = output
+        for line in output.splitlines():
+            if img_file + ':' in line:
+                reason = line.split(img_file + ':', 1)[1].strip()
+                break
+
+        return (False, reason)
+    else:
+        return (True, '')
+
+def verify_working_luks():
+    """
+    Skip test suite if LUKS does not work
+    """
+    (working, reason) = has_working_luks()
+    if not working:
+        notrun(reason)
+
 def qemu_pipe(*args):
     """
     Run qemu with an option to print something and exit (e.g. a help option).
-- 
2.26.2

Whenever running an iotest for the luks format, we should check whether
luks actually really works.

Tests that try to create luks-encrypted qcow2 images should do the same.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-7-mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 tests/qemu-iotests/087        | 1 +
 tests/qemu-iotests/178        | 1 +
 tests/qemu-iotests/188        | 1 +
 tests/qemu-iotests/189        | 1 +
 tests/qemu-iotests/198        | 1 +
 tests/qemu-iotests/206        | 1 +
 tests/qemu-iotests/263        | 1 +
 tests/qemu-iotests/284        | 1 +
 tests/qemu-iotests/common.rc  | 3 +++
 tests/qemu-iotests/iotests.py | 5 +++++
 10 files changed, 16 insertions(+)

diff --git a/tests/qemu-iotests/087 b/tests/qemu-iotests/087
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/087
+++ b/tests/qemu-iotests/087
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+_require_working_luks
 
 do_run_qemu()
 {
diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/178
+++ b/tests/qemu-iotests/178
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt raw qcow2
 _supported_proto file
 _supported_os Linux
+_require_working_luks
 
 echo "== Input validation =="
 echo
diff --git a/tests/qemu-iotests/188 b/tests/qemu-iotests/188
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/188
+++ b/tests/qemu-iotests/188
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _supported_os Linux
+_require_working_luks
 
 
 size=16M
diff --git a/tests/qemu-iotests/189 b/tests/qemu-iotests/189
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/189
+++ b/tests/qemu-iotests/189
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _supported_os Linux
+_require_working_luks
 
 
 size=16M
diff --git a/tests/qemu-iotests/198 b/tests/qemu-iotests/198
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/198
+++ b/tests/qemu-iotests/198
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _supported_os Linux
+_require_working_luks
 
 
 size=16M
diff --git a/tests/qemu-iotests/206 b/tests/qemu-iotests/206
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/206
+++ b/tests/qemu-iotests/206
@@ -XXX,XX +XXX,XX @@ import iotests
 from iotests import imgfmt
 
 iotests.script_initialize(supported_fmts=['qcow2'])
+iotests.verify_working_luks()
 
 with iotests.FilePath('t.qcow2') as disk_path, \
      iotests.FilePath('t.qcow2.base') as backing_path, \
diff --git a/tests/qemu-iotests/263 b/tests/qemu-iotests/263
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/263
+++ b/tests/qemu-iotests/263
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _supported_os Linux
+_require_working_luks
 
 
 size=1M
diff --git a/tests/qemu-iotests/284 b/tests/qemu-iotests/284
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/284
+++ b/tests/qemu-iotests/284
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _supported_os Linux
+_require_working_luks
 
 
 size=1M
diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -XXX,XX +XXX,XX @@ _supported_fmt()
     # setting IMGFMT_GENERIC to false.
     for f; do
         if [ "$f" = "$IMGFMT" -o "$f" = "generic" -a "$IMGFMT_GENERIC" = "true" ]; then
+            if [ "$IMGFMT" = "luks" ]; then
+                _require_working_luks
+            fi
             return
         fi
     done
diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -XXX,XX +XXX,XX @@ def _verify_image_format(supported_fmts: Sequence[str] = (),
         # similar to
         #   _supported_fmt generic
         # for bash tests
+        if imgfmt == 'luks':
+            verify_working_luks()
         return
 
     not_sup = supported_fmts and (imgfmt not in supported_fmts)
     if not_sup or (imgfmt in unsupported_fmts):
         notrun('not suitable for this image format: %s' % imgfmt)
 
+    if imgfmt == 'luks':
+        verify_working_luks()
+
 def _verify_protocol(supported: Sequence[str] = (),
                      unsupported: Sequence[str] = ()) -> None:
     assert not (supported and unsupported)
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

This will be used first to implement luks keyslot management.

block_crypto_amend_opts_init will be used to convert
qemu-img cmdline to QCryptoBlockAmendOptions

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20200608094030.670121-2-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qapi/crypto.json       | 16 ++++++++++++++++
 block/crypto.h         |  3 +++
 crypto/blockpriv.h     |  8 ++++++++
 include/crypto/block.h | 22 ++++++++++++++++++++++
 block/crypto.c         | 17 +++++++++++++++++
 crypto/block.c         | 29 +++++++++++++++++++++++++++++
 6 files changed, 95 insertions(+)

diff --git a/qapi/crypto.json b/qapi/crypto.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/crypto.json
+++ b/qapi/crypto.json
@@ -XXX,XX +XXX,XX @@
   'base': 'QCryptoBlockInfoBase',
   'discriminator': 'format',
   'data': { 'luks': 'QCryptoBlockInfoLUKS' } }
+
+
+
+##
+# @QCryptoBlockAmendOptions:
+#
+# The options that are available for all encryption formats
+# when amending encryption settings
+#
+# Since: 5.1
+##
+{ 'union': 'QCryptoBlockAmendOptions',
+  'base': 'QCryptoBlockOptionsBase',
+  'discriminator': 'format',
+  'data': {
+            } }
diff --git a/block/crypto.h b/block/crypto.h
index XXXXXXX..XXXXXXX 100644
--- a/block/crypto.h
+++ b/block/crypto.h
@@ -XXX,XX +XXX,XX @@
 QCryptoBlockCreateOptions *
 block_crypto_create_opts_init(QDict *opts, Error **errp);
 
+QCryptoBlockAmendOptions *
+block_crypto_amend_opts_init(QDict *opts, Error **errp);
+
 QCryptoBlockOpenOptions *
 block_crypto_open_opts_init(QDict *opts, Error **errp);
 
diff --git a/crypto/blockpriv.h b/crypto/blockpriv.h
index XXXXXXX..XXXXXXX 100644
--- a/crypto/blockpriv.h
+++ b/crypto/blockpriv.h
@@ -XXX,XX +XXX,XX @@ struct QCryptoBlockDriver {
                   void *opaque,
                   Error **errp);
 
+    int (*amend)(QCryptoBlock *block,
+                 QCryptoBlockReadFunc readfunc,
+                 QCryptoBlockWriteFunc writefunc,
+                 void *opaque,
+                 QCryptoBlockAmendOptions *options,
+                 bool force,
+                 Error **errp);
+
     int (*get_info)(QCryptoBlock *block,
                     QCryptoBlockInfo *info,
                     Error **errp);
diff --git a/include/crypto/block.h b/include/crypto/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/crypto/block.h
+++ b/include/crypto/block.h
@@ -XXX,XX +XXX,XX @@ QCryptoBlock *qcrypto_block_create(QCryptoBlockCreateOptions *options,
                                    void *opaque,
                                    Error **errp);
 
+/**
+ * qcrypto_block_amend_options:
+ * @block: the block encryption object
+ *
+ * @readfunc: callback for reading data from the volume header
+ * @writefunc: callback for writing data to the volume header
+ * @opaque: data to pass to @readfunc and @writefunc
+ * @options: the new/amended encryption options
+ * @force: hint for the driver to allow unsafe operation
+ * @errp: error pointer
+ *
+ * Changes the crypto options of the encryption format
+ *
+ */
+int qcrypto_block_amend_options(QCryptoBlock *block,
+                                QCryptoBlockReadFunc readfunc,
+                                QCryptoBlockWriteFunc writefunc,
+                                void *opaque,
+                                QCryptoBlockAmendOptions *options,
+                                bool force,
+                                Error **errp);
+
 
 /**
  * qcrypto_block_calculate_payload_offset:
diff --git a/block/crypto.c b/block/crypto.c
index XXXXXXX..XXXXXXX 100644
--- a/block/crypto.c
+++ b/block/crypto.c
@@ -XXX,XX +XXX,XX @@ block_crypto_create_opts_init(QDict *opts, Error **errp)
     return ret;
 }
 
+QCryptoBlockAmendOptions *
+block_crypto_amend_opts_init(QDict *opts, Error **errp)
+{
+    Visitor *v;
+    QCryptoBlockAmendOptions *ret;
+
+    v = qobject_input_visitor_new_flat_confused(opts, errp);
+    if (!v) {
+        return NULL;
+    }
+
+    visit_type_QCryptoBlockAmendOptions(v, NULL, &ret, errp);
+
+    visit_free(v);
+    return ret;
+}
+
 
 static int block_crypto_open_generic(QCryptoBlockFormat format,
                                      QemuOptsList *opts_spec,
diff --git a/crypto/block.c b/crypto/block.c
index XXXXXXX..XXXXXXX 100644
--- a/crypto/block.c
+++ b/crypto/block.c
@@ -XXX,XX +XXX,XX @@ qcrypto_block_calculate_payload_offset(QCryptoBlockCreateOptions *create_opts,
     return crypto != NULL;
 }
 
+int qcrypto_block_amend_options(QCryptoBlock *block,
+                                QCryptoBlockReadFunc readfunc,
+                                QCryptoBlockWriteFunc writefunc,
+                                void *opaque,
+                                QCryptoBlockAmendOptions *options,
+                                bool force,
+                                Error **errp)
+{
+    if (options->format != block->format) {
+        error_setg(errp,
+                   "Cannot amend encryption format");
+        return -1;
+    }
+
+    if (!block->driver->amend) {
+        error_setg(errp,
+                   "Crypto format %s doesn't support format options amendment",
+                   QCryptoBlockFormat_str(block->format));
+        return -1;
+    }
+
+    return block->driver->amend(block,
+                                readfunc,
+                                writefunc,
+                                opaque,
+                                options,
+                                force,
+                                errp);
+}
 
 QCryptoBlockInfo *qcrypto_block_get_info(QCryptoBlock *block,
                                          Error **errp)
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

Next few patches will expose that functionality to the user.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20200608094030.670121-3-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qapi/crypto.json    |  59 ++++++-
 crypto/block-luks.c | 416 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 469 insertions(+), 6 deletions(-)

diff --git a/qapi/crypto.json b/qapi/crypto.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/crypto.json
+++ b/qapi/crypto.json
@@ -XXX,XX +XXX,XX @@
            'uuid': 'str',
            'slots': [ 'QCryptoBlockInfoLUKSSlot' ] }}
 
-
 ##
 # @QCryptoBlockInfo:
 #
@@ -XXX,XX +XXX,XX @@
   'discriminator': 'format',
   'data': { 'luks': 'QCryptoBlockInfoLUKS' } }
 
+##
+# @QCryptoBlockLUKSKeyslotState:
+#
+# Defines state of keyslots that are affected by the update
+#
+# @active:    The slots contain the given password and marked as active
+# @inactive:  The slots are erased (contain garbage) and marked as inactive
+#
+# Since: 5.1
+##
+{ 'enum': 'QCryptoBlockLUKSKeyslotState',
+  'data': [ 'active', 'inactive' ] }
+
 
+##
+# @QCryptoBlockAmendOptionsLUKS:
+#
+# This struct defines the update parameters that activate/de-activate set
+# of keyslots
+#
+# @state: the desired state of the keyslots
+#
+# @new-secret:    The ID of a QCryptoSecret object providing the password to be
+#                 written into added active keyslots
+#
+# @old-secret:    Optional (for deactivation only)
+#                 If given will deactive all keyslots that
+#                 match password located in QCryptoSecret with this ID
+#
+# @iter-time:     Optional (for activation only)
+#                 Number of milliseconds to spend in
+#                 PBKDF passphrase processing for the newly activated keyslot.
+#                 Currently defaults to 2000.
+#
+# @keyslot:       Optional. ID of the keyslot to activate/deactivate.
+#                 For keyslot activation, keyslot should not be active already
+#                 (this is unsafe to update an active keyslot),
+#                 but possible if 'force' parameter is given.
+#                 If keyslot is not given, first free keyslot will be written.
+#
+#                 For keyslot deactivation, this parameter specifies the exact
+#                 keyslot to deactivate
+#
+# @secret:        Optional. The ID of a QCryptoSecret object providing the
+#                 password to use to retrive current master key.
+#                 Defaults to the same secret that was used to open the image
+#
+#
+# Since 5.1
+##
+{ 'struct': 'QCryptoBlockAmendOptionsLUKS',
+  'data': { 'state': 'QCryptoBlockLUKSKeyslotState',
+            '*new-secret': 'str',
+            '*old-secret': 'str',
+            '*keyslot': 'int',
+            '*iter-time': 'int',
+            '*secret': 'str' } }
 
 ##
 # @QCryptoBlockAmendOptions:
@@ -XXX,XX +XXX,XX @@
   'base': 'QCryptoBlockOptionsBase',
   'discriminator': 'format',
   'data': {
-            } }
+          'luks': 'QCryptoBlockAmendOptionsLUKS' } }
diff --git a/crypto/block-luks.c b/crypto/block-luks.c
index XXXXXXX..XXXXXXX 100644
--- a/crypto/block-luks.c
+++ b/crypto/block-luks.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/uuid.h"
 
 #include "qemu/coroutine.h"
+#include "qemu/bitmap.h"
 
 /*
  * Reference for the LUKS format implemented here is
@@ -XXX,XX +XXX,XX @@ typedef struct QCryptoBlockLUKSKeySlot QCryptoBlockLUKSKeySlot;
 
 #define QCRYPTO_BLOCK_LUKS_SECTOR_SIZE 512LL
 
+#define QCRYPTO_BLOCK_LUKS_DEFAULT_ITER_TIME_MS 2000
+#define QCRYPTO_BLOCK_LUKS_ERASE_ITERATIONS 40
+
 static const char qcrypto_block_luks_magic[QCRYPTO_BLOCK_LUKS_MAGIC_LEN] = {
     'L', 'U', 'K', 'S', 0xBA, 0xBE
 };
@@ -XXX,XX +XXX,XX @@ struct QCryptoBlockLUKS {
 
     /* Hash algorithm used in pbkdf2 function */
     QCryptoHashAlgorithm hash_alg;
+
+    /* Name of the secret that was used to open the image */
+    char *secret;
 };
 
 
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_store_key(QCryptoBlock *block,
                              Error **errp)
 {
     QCryptoBlockLUKS *luks = block->opaque;
-    QCryptoBlockLUKSKeySlot *slot = &luks->header.key_slots[slot_idx];
+    QCryptoBlockLUKSKeySlot *slot;
     g_autofree uint8_t *splitkey = NULL;
     size_t splitkeylen;
     g_autofree uint8_t *slotkey = NULL;
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_store_key(QCryptoBlock *block,
     uint64_t iters;
     int ret = -1;
 
+    assert(slot_idx < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS);
+    slot = &luks->header.key_slots[slot_idx];
     if (qcrypto_random_bytes(slot->salt,
                              QCRYPTO_BLOCK_LUKS_SALT_LEN,
                              errp) < 0) {
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_load_key(QCryptoBlock *block,
                             Error **errp)
 {
     QCryptoBlockLUKS *luks = block->opaque;
-    const QCryptoBlockLUKSKeySlot *slot = &luks->header.key_slots[slot_idx];
+    const QCryptoBlockLUKSKeySlot *slot;
     g_autofree uint8_t *splitkey = NULL;
     size_t splitkeylen;
     g_autofree uint8_t *possiblekey = NULL;
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_load_key(QCryptoBlock *block,
     g_autoptr(QCryptoIVGen) ivgen = NULL;
     size_t niv;
 
+    assert(slot_idx < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS);
+    slot = &luks->header.key_slots[slot_idx];
     if (slot->active != QCRYPTO_BLOCK_LUKS_KEY_SLOT_ENABLED) {
         return 0;
     }
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_find_key(QCryptoBlock *block,
     return -1;
 }
 
+/*
+ * Returns true if a slot i is marked as active
+ * (contains encrypted copy of the master key)
+ */
+static bool
+qcrypto_block_luks_slot_active(const QCryptoBlockLUKS *luks,
+                               unsigned int slot_idx)
+{
+    uint32_t val;
+
+    assert(slot_idx < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS);
+    val = luks->header.key_slots[slot_idx].active;
+    return val == QCRYPTO_BLOCK_LUKS_KEY_SLOT_ENABLED;
+}
+
+/*
+ * Returns the number of slots that are marked as active
+ * (slots that contain encrypted copy of the master key)
+ */
+static unsigned int
+qcrypto_block_luks_count_active_slots(const QCryptoBlockLUKS *luks)
+{
+    size_t i = 0;
+    unsigned int ret = 0;
+
+    for (i = 0; i < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS; i++) {
+        if (qcrypto_block_luks_slot_active(luks, i)) {
+            ret++;
+        }
+    }
+    return ret;
+}
+
+/*
+ * Finds first key slot which is not active
+ * Returns the key slot index, or -1 if it doesn't exist
+ */
+static int
+qcrypto_block_luks_find_free_keyslot(const QCryptoBlockLUKS *luks)
+{
+    size_t i;
+
+    for (i = 0; i < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS; i++) {
+        if (!qcrypto_block_luks_slot_active(luks, i)) {
+            return i;
+        }
+    }
+    return -1;
+}
+
+/*
+ * Erases an keyslot given its index
+ * Returns:
+ *    0 if the keyslot was erased successfully
+ *   -1 if a error occurred while erasing the keyslot
+ *
+ */
+static int
+qcrypto_block_luks_erase_key(QCryptoBlock *block,
+                             unsigned int slot_idx,
+                             QCryptoBlockWriteFunc writefunc,
+                             void *opaque,
+                             Error **errp)
+{
+    QCryptoBlockLUKS *luks = block->opaque;
+    QCryptoBlockLUKSKeySlot *slot;
+    g_autofree uint8_t *garbagesplitkey = NULL;
+    size_t splitkeylen;
+    size_t i;
+    Error *local_err = NULL;
+    int ret;
+
+    assert(slot_idx < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS);
+    slot = &luks->header.key_slots[slot_idx];
+
+    splitkeylen = luks->header.master_key_len * slot->stripes;
+    assert(splitkeylen > 0);
+
+    garbagesplitkey = g_new0(uint8_t, splitkeylen);
+
+    /* Reset the key slot header */
+    memset(slot->salt, 0, QCRYPTO_BLOCK_LUKS_SALT_LEN);
+    slot->iterations = 0;
+    slot->active = QCRYPTO_BLOCK_LUKS_KEY_SLOT_DISABLED;
+
+    ret = qcrypto_block_luks_store_header(block, writefunc,
+                                          opaque, &local_err);
+
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+    }
+    /*
+     * Now try to erase the key material, even if the header
+     * update failed
+     */
+    for (i = 0; i < QCRYPTO_BLOCK_LUKS_ERASE_ITERATIONS; i++) {
+        if (qcrypto_random_bytes(garbagesplitkey,
+                                 splitkeylen, &local_err) < 0) {
+            /*
+             * If we failed to get the random data, still write
+             * at least zeros to the key slot at least once
+             */
+            error_propagate(errp, local_err);
+
+            if (i > 0) {
+                return -1;
+            }
+        }
+        if (writefunc(block,
+                      slot->key_offset_sector * QCRYPTO_BLOCK_LUKS_SECTOR_SIZE,
+                      garbagesplitkey,
+                      splitkeylen,
+                      opaque,
+                      &local_err) != splitkeylen) {
+            error_propagate(errp, local_err);
+            return -1;
+        }
+    }
+    return ret;
+}
 
 static int
 qcrypto_block_luks_open(QCryptoBlock *block,
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_open(QCryptoBlock *block,
 
     luks = g_new0(QCryptoBlockLUKS, 1);
     block->opaque = luks;
+    luks->secret = g_strdup(options->u.luks.key_secret);
 
     if (qcrypto_block_luks_load_header(block, readfunc, opaque, errp) < 0) {
         goto fail;
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_open(QCryptoBlock *block,
  fail:
     qcrypto_block_free_cipher(block);
     qcrypto_ivgen_free(block->ivgen);
+    g_free(luks->secret);
     g_free(luks);
     return -1;
 }
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_create(QCryptoBlock *block,
 
     memcpy(&luks_opts, &options->u.luks, sizeof(luks_opts));
     if (!luks_opts.has_iter_time) {
-        luks_opts.iter_time = 2000;
+        luks_opts.iter_time = QCRYPTO_BLOCK_LUKS_DEFAULT_ITER_TIME_MS;
     }
     if (!luks_opts.has_cipher_alg) {
         luks_opts.cipher_alg = QCRYPTO_CIPHER_ALG_AES_256;
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_create(QCryptoBlock *block,
                    optprefix ? optprefix : "");
         goto error;
     }
+    luks->secret = g_strdup(options->u.luks.key_secret);
+
     password = qcrypto_secret_lookup_as_utf8(luks_opts.key_secret, errp);
     if (!password) {
         goto error;
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_create(QCryptoBlock *block,
     qcrypto_block_free_cipher(block);
     qcrypto_ivgen_free(block->ivgen);
 
+    g_free(luks->secret);
     g_free(luks);
     return -1;
 }
 
+static int
+qcrypto_block_luks_amend_add_keyslot(QCryptoBlock *block,
+                                     QCryptoBlockReadFunc readfunc,
+                                     QCryptoBlockWriteFunc writefunc,
+                                     void *opaque,
+                                     QCryptoBlockAmendOptionsLUKS *opts_luks,
+                                     bool force,
+                                     Error **errp)
+{
+    QCryptoBlockLUKS *luks = block->opaque;
+    uint64_t iter_time = opts_luks->has_iter_time ?
+                         opts_luks->iter_time :
+                         QCRYPTO_BLOCK_LUKS_DEFAULT_ITER_TIME_MS;
+    int keyslot;
+    g_autofree char *old_password = NULL;
+    g_autofree char *new_password = NULL;
+    g_autofree uint8_t *master_key = NULL;
+
+    char *secret = opts_luks->has_secret ? opts_luks->secret : luks->secret;
+
+    if (!opts_luks->has_new_secret) {
+        error_setg(errp, "'new-secret' is required to activate a keyslot");
+        return -1;
+    }
+    if (opts_luks->has_old_secret) {
+        error_setg(errp,
+                   "'old-secret' must not be given when activating keyslots");
+        return -1;
+    }
+
+    if (opts_luks->has_keyslot) {
+        keyslot = opts_luks->keyslot;
+        if (keyslot < 0 || keyslot >= QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS) {
+            error_setg(errp,
+                       "Invalid keyslot %u specified, must be between 0 and %u",
+                       keyslot, QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS - 1);
+            return -1;
+        }
+    } else {
+        keyslot = qcrypto_block_luks_find_free_keyslot(luks);
+        if (keyslot == -1) {
+            error_setg(errp,
+                       "Can't add a keyslot - all keyslots are in use");
+            return -1;
+        }
+    }
+
+    if (!force && qcrypto_block_luks_slot_active(luks, keyslot)) {
+        error_setg(errp,
+                   "Refusing to overwrite active keyslot %i - "
+                   "please erase it first",
+                   keyslot);
+        return -1;
+    }
+
+    /* Locate the password that will be used to retrieve the master key */
+    old_password = qcrypto_secret_lookup_as_utf8(secret, errp);
+    if (!old_password) {
+        return -1;
+    }
+
+    /* Retrieve the master key */
+    master_key = g_new0(uint8_t, luks->header.master_key_len);
+
+    if (qcrypto_block_luks_find_key(block, old_password, master_key,
+                                    readfunc, opaque, errp) < 0) {
+        error_append_hint(errp, "Failed to retrieve the master key");
+        return -1;
+    }
+
+    /* Locate the new password*/
+    new_password = qcrypto_secret_lookup_as_utf8(opts_luks->new_secret, errp);
+    if (!new_password) {
+        return -1;
+    }
+
+    /* Now set the new keyslots */
+    if (qcrypto_block_luks_store_key(block, keyslot, new_password, master_key,
+                                     iter_time, writefunc, opaque, errp)) {
+        error_append_hint(errp, "Failed to write to keyslot %i", keyslot);
+        return -1;
+    }
+    return 0;
+}
+
+static int
+qcrypto_block_luks_amend_erase_keyslots(QCryptoBlock *block,
+                                        QCryptoBlockReadFunc readfunc,
+                                        QCryptoBlockWriteFunc writefunc,
+                                        void *opaque,
+                                        QCryptoBlockAmendOptionsLUKS *opts_luks,
+                                        bool force,
+                                        Error **errp)
+{
+    QCryptoBlockLUKS *luks = block->opaque;
+    g_autofree uint8_t *tmpkey = NULL;
+    g_autofree char *old_password = NULL;
+
+    if (opts_luks->has_new_secret) {
+        error_setg(errp,
+                   "'new-secret' must not be given when erasing keyslots");
+        return -1;
+    }
+    if (opts_luks->has_iter_time) {
+        error_setg(errp,
+                   "'iter-time' must not be given when erasing keyslots");
+        return -1;
+    }
+    if (opts_luks->has_secret) {
+        error_setg(errp,
+                   "'secret' must not be given when erasing keyslots");
+        return -1;
+    }
+
+    /* Load the old password if given */
+    if (opts_luks->has_old_secret) {
+        old_password = qcrypto_secret_lookup_as_utf8(opts_luks->old_secret,
+                                                     errp);
+        if (!old_password) {
+            return -1;
+        }
+
+        /*
+         * Allocate a temporary key buffer that we will need when
+         * checking if slot matches the given old password
+         */
+        tmpkey = g_new0(uint8_t, luks->header.master_key_len);
+    }
+
+    /* Erase an explicitly given keyslot */
+    if (opts_luks->has_keyslot) {
+        int keyslot = opts_luks->keyslot;
+
+        if (keyslot < 0 || keyslot >= QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS) {
+            error_setg(errp,
+                       "Invalid keyslot %i specified, must be between 0 and %i",
+                       keyslot, QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS - 1);
+            return -1;
+        }
+
+        if (opts_luks->has_old_secret) {
+            int rv = qcrypto_block_luks_load_key(block,
+                                                 keyslot,
+                                                 old_password,
+                                                 tmpkey,
+                                                 readfunc,
+                                                 opaque,
+                                                 errp);
+            if (rv == -1) {
+                return -1;
+            } else if (rv == 0) {
+                error_setg(errp,
+                           "Given keyslot %i doesn't contain the given "
+                           "old password for erase operation",
+                           keyslot);
+                return -1;
+            }
+        }
+
+        if (!force && !qcrypto_block_luks_slot_active(luks, keyslot)) {
+            error_setg(errp,
+                       "Given keyslot %i is already erased (inactive) ",
+                       keyslot);
+            return -1;
+        }
+
+        if (!force && qcrypto_block_luks_count_active_slots(luks) == 1) {
+            error_setg(errp,
+                       "Attempt to erase the only active keyslot %i "
+                       "which will erase all the data in the image "
+                       "irreversibly - refusing operation",
+                       keyslot);
+            return -1;
+        }
+
+        if (qcrypto_block_luks_erase_key(block, keyslot,
+                                         writefunc, opaque, errp)) {
+            error_append_hint(errp, "Failed to erase keyslot %i", keyslot);
+            return -1;
+        }
+
+    /* Erase all keyslots that match the given old password */
+    } else if (opts_luks->has_old_secret) {
+
+        unsigned long slots_to_erase_bitmap = 0;
+        size_t i;
+        int slot_count;
+
+        assert(QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS <=
+               sizeof(slots_to_erase_bitmap) * 8);
+
+        for (i = 0; i < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS; i++) {
+            int rv = qcrypto_block_luks_load_key(block,
+                                                 i,
+                                                 old_password,
+                                                 tmpkey,
+                                                 readfunc,
+                                                 opaque,
+                                                 errp);
+            if (rv == -1) {
+                return -1;
+            } else if (rv == 1) {
+                bitmap_set(&slots_to_erase_bitmap, i, 1);
+            }
+        }
+
+        slot_count = bitmap_count_one(&slots_to_erase_bitmap,
+                                      QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS);
+        if (slot_count == 0) {
+            error_setg(errp,
+                       "No keyslots match given (old) password for erase operation");
+            return -1;
+        }
+
+        if (!force &&
+            slot_count == qcrypto_block_luks_count_active_slots(luks)) {
+            error_setg(errp,
+                       "All the active keyslots match the (old) password that "
+                       "was given and erasing them will erase all the data in "
+                       "the image irreversibly - refusing operation");
+            return -1;
+        }
+
+        /* Now apply the update */
+        for (i = 0; i < QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS; i++) {
+            if (!test_bit(i, &slots_to_erase_bitmap)) {
+                continue;
+            }
+            if (qcrypto_block_luks_erase_key(block, i, writefunc,
+                opaque, errp)) {
+                error_append_hint(errp, "Failed to erase keyslot %zu", i);
+                return -1;
+            }
+        }
+    } else {
+        error_setg(errp,
+                   "To erase keyslot(s), either explicit keyslot index "
+                   "or the password currently contained in them must be given");
+        return -1;
+    }
+    return 0;
+}
+
+static int
+qcrypto_block_luks_amend_options(QCryptoBlock *block,
+                                 QCryptoBlockReadFunc readfunc,
+                                 QCryptoBlockWriteFunc writefunc,
+                                 void *opaque,
+                                 QCryptoBlockAmendOptions *options,
+                                 bool force,
+                                 Error **errp)
+{
+    QCryptoBlockAmendOptionsLUKS *opts_luks = &options->u.luks;
+
+    switch (opts_luks->state) {
+    case Q_CRYPTO_BLOCKLUKS_KEYSLOT_STATE_ACTIVE:
+        return qcrypto_block_luks_amend_add_keyslot(block, readfunc,
+                                                    writefunc, opaque,
+                                                    opts_luks, force, errp);
+    case Q_CRYPTO_BLOCKLUKS_KEYSLOT_STATE_INACTIVE:
+        return qcrypto_block_luks_amend_erase_keyslots(block, readfunc,
+                                                       writefunc, opaque,
+                                                       opts_luks, force, errp);
+    default:
+        g_assert_not_reached();
+    }
+}
 
 static int qcrypto_block_luks_get_info(QCryptoBlock *block,
                                        QCryptoBlockInfo *info,
@@ -XXX,XX +XXX,XX @@ static int qcrypto_block_luks_get_info(QCryptoBlock *block,
 
 static void qcrypto_block_luks_cleanup(QCryptoBlock *block)
 {
-    g_free(block->opaque);
+    QCryptoBlockLUKS *luks = block->opaque;
+    if (luks) {
+        g_free(luks->secret);
+        g_free(luks);
+    }
 }
 
 
@@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_encrypt(QCryptoBlock *block,
 const QCryptoBlockDriver qcrypto_block_driver_luks = {
     .open = qcrypto_block_luks_open,
     .create = qcrypto_block_luks_create,
+    .amend = qcrypto_block_luks_amend_options,
     .get_info = qcrypto_block_luks_get_info,
     .cleanup = qcrypto_block_luks_cleanup,
     .decrypt = qcrypto_block_luks_decrypt,
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

'force' option will be used for some unsafe amend operations.

This includes things like erasing last keyslot in luks based formats
(which destroys the data, unless the master key is backed up
by external means), but that _might_ be desired result.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200608094030.670121-4-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 docs/tools/qemu-img.rst   | 5 ++++-
 include/block/block.h     | 1 +
 include/block/block_int.h | 1 +
 block.c                   | 4 +++-
 block/qcow2.c             | 1 +
 qemu-img.c                | 8 +++++++-
 qemu-img-cmds.hx          | 4 ++--
 7 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/docs/tools/qemu-img.rst b/docs/tools/qemu-img.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/tools/qemu-img.rst
+++ b/docs/tools/qemu-img.rst
@@ -XXX,XX +XXX,XX @@ Command description:
 
 .. program:: qemu-img-commands
 
-.. option:: amend [--object OBJECTDEF] [--image-opts] [-p] [-q] [-f FMT] [-t CACHE] -o OPTIONS FILENAME
+.. option:: amend [--object OBJECTDEF] [--image-opts] [-p] [-q] [-f FMT] [-t CACHE] [--force] -o OPTIONS FILENAME
 
   Amends the image format specific *OPTIONS* for the image file
   *FILENAME*. Not all file formats support this operation.
 
+  --force allows some unsafe operations. Currently for -f luks, it allows to
+  erase the last encryption key, and to overwrite an active encryption key.
+
 .. option:: bench [-c COUNT] [-d DEPTH] [-f FMT] [--flush-interval=FLUSH_INTERVAL] [-i AIO] [-n] [--no-drain] [-o OFFSET] [--pattern=PATTERN] [-q] [-s BUFFER_SIZE] [-S STEP_SIZE] [-t CACHE] [-w] [-U] FILENAME
 
   Run a simple sequential I/O benchmark on the specified image. If ``-w`` is
diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ typedef void BlockDriverAmendStatusCB(BlockDriverState *bs, int64_t offset,
                                       int64_t total_work_size, void *opaque);
 int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts,
                        BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
+                       bool force,
                        Error **errp);
 
 /* check if a named node can be replaced when doing drive-mirror */
diff --git a/include/block/block_int.h b/include/block/block_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -XXX,XX +XXX,XX @@ struct BlockDriver {
     int (*bdrv_amend_options)(BlockDriverState *bs, QemuOpts *opts,
                               BlockDriverAmendStatusCB *status_cb,
                               void *cb_opaque,
+                              bool force,
                               Error **errp);
 
     void (*bdrv_debug_event)(BlockDriverState *bs, BlkdebugEvent event);
diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
 
 int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
                        BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
+                       bool force,
                        Error **errp)
 {
     if (!bs->drv) {
@@ -XXX,XX +XXX,XX @@ int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
                    bs->drv->format_name);
         return -ENOTSUP;
     }
-    return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque, errp);
+    return bs->drv->bdrv_amend_options(bs, opts, status_cb,
+                                       cb_opaque, force, errp);
 }
 
 /*
diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ static void qcow2_amend_helper_cb(BlockDriverState *bs,
 static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
                                BlockDriverAmendStatusCB *status_cb,
                                void *cb_opaque,
+                               bool force,
                                Error **errp)
 {
     BDRVQcow2State *s = bs->opaque;
diff --git a/qemu-img.c b/qemu-img.c
index XXXXXXX..XXXXXXX 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -XXX,XX +XXX,XX @@ enum {
     OPTION_DISABLE = 273,
     OPTION_MERGE = 274,
     OPTION_BITMAPS = 275,
+    OPTION_FORCE = 276,
 };
 
 typedef enum OutputFormat {
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
     BlockBackend *blk = NULL;
     BlockDriverState *bs = NULL;
     bool image_opts = false;
+    bool force = false;
 
     cache = BDRV_DEFAULT_CACHE;
     for (;;) {
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
             {"help", no_argument, 0, 'h'},
             {"object", required_argument, 0, OPTION_OBJECT},
             {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
+            {"force", no_argument, 0, OPTION_FORCE},
             {0, 0, 0, 0}
         };
         c = getopt_long(argc, argv, ":ho:f:t:pq",
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
         case OPTION_IMAGE_OPTS:
             image_opts = true;
             break;
+        case OPTION_FORCE:
+            force = true;
+            break;
         }
     }
 
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
 
     /* In case the driver does not call amend_status_cb() */
     qemu_progress_print(0.f, 0);
-    ret = bdrv_amend_options(bs, opts, &amend_status_cb, NULL, &err);
+    ret = bdrv_amend_options(bs, opts, &amend_status_cb, NULL, force, &err);
     qemu_progress_print(100.f, 0);
     if (ret < 0) {
         error_report_err(err);
diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
index XXXXXXX..XXXXXXX 100644
--- a/qemu-img-cmds.hx
+++ b/qemu-img-cmds.hx
@@ -XXX,XX +XXX,XX @@ HXCOMM When amending the rST sections, please remember to copy the usage
 HXCOMM over to the per-command sections in docs/tools/qemu-img.rst.
 
 DEF("amend", img_amend,
-    "amend [--object objectdef] [--image-opts] [-p] [-q] [-f fmt] [-t cache] -o options filename")
+    "amend [--object objectdef] [--image-opts] [-p] [-q] [-f fmt] [-t cache] [--force] -o options filename")
 SRST
-.. option:: amend [--object OBJECTDEF] [--image-opts] [-p] [-q] [-f FMT] [-t CACHE] -o OPTIONS FILENAME
+.. option:: amend [--object OBJECTDEF] [--image-opts] [-p] [-q] [-f FMT] [-t CACHE] [--force] -o OPTIONS FILENAME
 ERST
 
 DEF("bench", img_bench,
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

Some options are only useful for creation
(or hard to be amended, like cluster size for qcow2), while some other
options are only useful for amend, like upcoming keyslot management
options for luks

Since currently only qcow2 supports amend, move all its options
to a common macro and then include it in each action option list.

In future it might be useful to remove some options which are
not supported anyway from amend list, which currently
cause an error message if amended.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200608094030.670121-5-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block_int.h |   4 +
 block/qcow2.c             | 173 +++++++++++++++++++++-----------------
 qemu-img.c                |  18 ++--
 3 files changed, 107 insertions(+), 88 deletions(-)

diff --git a/include/block/block_int.h b/include/block/block_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -XXX,XX +XXX,XX @@ struct BlockDriver {
 
     /* List of options for creating images, terminated by name == NULL */
     QemuOptsList *create_opts;
+
+    /* List of options for image amend */
+    QemuOptsList *amend_opts;
+
     /*
      * If this driver supports reopening images this contains a
      * NULL-terminated list of the runtime options that can be
diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
     s->signaled_corruption = true;
 }
 
+#define QCOW_COMMON_OPTIONS                                         \
+    {                                                               \
+        .name = BLOCK_OPT_SIZE,                                     \
+        .type = QEMU_OPT_SIZE,                                      \
+        .help = "Virtual disk size"                                 \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_COMPAT_LEVEL,                             \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "Compatibility level (v2 [0.10] or v3 [1.1])"       \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_BACKING_FILE,                             \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "File name of a base image"                         \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_BACKING_FMT,                              \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "Image format of the base image"                    \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_DATA_FILE,                                \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "File name of an external data file"                \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_DATA_FILE_RAW,                            \
+        .type = QEMU_OPT_BOOL,                                      \
+        .help = "The external data file must stay valid "           \
+                "as a raw image"                                    \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_ENCRYPT,                                  \
+        .type = QEMU_OPT_BOOL,                                      \
+        .help = "Encrypt the image with format 'aes'. (Deprecated " \
+                "in favor of " BLOCK_OPT_ENCRYPT_FORMAT "=aes)",    \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_ENCRYPT_FORMAT,                           \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "Encrypt the image, format choices: 'aes', 'luks'", \
+    },                                                              \
+    BLOCK_CRYPTO_OPT_DEF_KEY_SECRET("encrypt.",                     \
+        "ID of secret providing qcow AES key or LUKS passphrase"),  \
+    BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_ALG("encrypt."),               \
+    BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_MODE("encrypt."),              \
+    BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_ALG("encrypt."),                \
+    BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_HASH_ALG("encrypt."),           \
+    BLOCK_CRYPTO_OPT_DEF_LUKS_HASH_ALG("encrypt."),                 \
+    BLOCK_CRYPTO_OPT_DEF_LUKS_ITER_TIME("encrypt."),                \
+    {                                                               \
+        .name = BLOCK_OPT_CLUSTER_SIZE,                             \
+        .type = QEMU_OPT_SIZE,                                      \
+        .help = "qcow2 cluster size",                               \
+        .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)            \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_PREALLOC,                                 \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "Preallocation mode (allowed values: off, "         \
+                "metadata, falloc, full)"                           \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_LAZY_REFCOUNTS,                           \
+        .type = QEMU_OPT_BOOL,                                      \
+        .help = "Postpone refcount updates",                        \
+        .def_value_str = "off"                                      \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_REFCOUNT_BITS,                            \
+        .type = QEMU_OPT_NUMBER,                                    \
+        .help = "Width of a reference count entry in bits",         \
+        .def_value_str = "16"                                       \
+    },                                                              \
+    {                                                               \
+        .name = BLOCK_OPT_COMPRESSION_TYPE,                         \
+        .type = QEMU_OPT_STRING,                                    \
+        .help = "Compression method used for image cluster "        \
+                "compression",                                      \
+        .def_value_str = "zlib"                                     \
+    }
+
 static QemuOptsList qcow2_create_opts = {
     .name = "qcow2-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(qcow2_create_opts.head),
     .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_COMPAT_LEVEL,
-            .type = QEMU_OPT_STRING,
-            .help = "Compatibility level (v2 [0.10] or v3 [1.1])"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FMT,
-            .type = QEMU_OPT_STRING,
-            .help = "Image format of the base image"
-        },
-        {
-            .name = BLOCK_OPT_DATA_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of an external data file"
-        },
-        {
-            .name = BLOCK_OPT_DATA_FILE_RAW,
-            .type = QEMU_OPT_BOOL,
-            .help = "The external data file must stay valid as a raw image"
-        },
-        {
-            .name = BLOCK_OPT_ENCRYPT,
-            .type = QEMU_OPT_BOOL,
-            .help = "Encrypt the image with format 'aes'. (Deprecated "
-                    "in favor of " BLOCK_OPT_ENCRYPT_FORMAT "=aes)",
-        },
-        {
-            .name = BLOCK_OPT_ENCRYPT_FORMAT,
-            .type = QEMU_OPT_STRING,
-            .help = "Encrypt the image, format choices: 'aes', 'luks'",
-        },
-        BLOCK_CRYPTO_OPT_DEF_KEY_SECRET("encrypt.",
-            "ID of secret providing qcow AES key or LUKS passphrase"),
-        BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_ALG("encrypt."),
-        BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_MODE("encrypt."),
-        BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_ALG("encrypt."),
-        BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_HASH_ALG("encrypt."),
-        BLOCK_CRYPTO_OPT_DEF_LUKS_HASH_ALG("encrypt."),
-        BLOCK_CRYPTO_OPT_DEF_LUKS_ITER_TIME("encrypt."),
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "qcow2 cluster size",
-            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)
-        },
-        {
-            .name = BLOCK_OPT_PREALLOC,
-            .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, metadata, "
-                    "falloc, full)"
-        },
-        {
-            .name = BLOCK_OPT_LAZY_REFCOUNTS,
-            .type = QEMU_OPT_BOOL,
-            .help = "Postpone refcount updates",
-            .def_value_str = "off"
-        },
-        {
-            .name = BLOCK_OPT_REFCOUNT_BITS,
-            .type = QEMU_OPT_NUMBER,
-            .help = "Width of a reference count entry in bits",
-            .def_value_str = "16"
-        },
-        {
-            .name = BLOCK_OPT_COMPRESSION_TYPE,
-            .type = QEMU_OPT_STRING,
-            .help = "Compression method used for image cluster compression",
-            .def_value_str = "zlib"
-        },
+        QCOW_COMMON_OPTIONS,
+        { /* end of list */ }
+    }
+};
+
+static QemuOptsList qcow2_amend_opts = {
+    .name = "qcow2-amend-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(qcow2_amend_opts.head),
+    .desc = {
+        QCOW_COMMON_OPTIONS,
         { /* end of list */ }
     }
 };
@@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_qcow2 = {
     .bdrv_inactivate            = qcow2_inactivate,
 
     .create_opts         = &qcow2_create_opts,
+    .amend_opts          = &qcow2_amend_opts,
     .strong_runtime_opts = qcow2_strong_runtime_opts,
     .mutable_opts        = mutable_opts,
     .bdrv_co_check       = qcow2_co_check,
diff --git a/qemu-img.c b/qemu-img.c
index XXXXXXX..XXXXXXX 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -XXX,XX +XXX,XX @@ static int print_amend_option_help(const char *format)
         return 1;
     }
 
-    /* Every driver supporting amendment must have create_opts */
-    assert(drv->create_opts);
+    /* Every driver supporting amendment must have amend_opts */
+    assert(drv->amend_opts);
 
     printf("Creation options for '%s':\n", format);
-    qemu_opts_print_help(drv->create_opts, false);
+    qemu_opts_print_help(drv->amend_opts, false);
     printf("\nNote that not all of these options may be amendable.\n");
     return 0;
 }
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
     Error *err = NULL;
     int c, ret = 0;
     char *options = NULL;
-    QemuOptsList *create_opts = NULL;
+    QemuOptsList *amend_opts = NULL;
     QemuOpts *opts = NULL;
     const char *fmt = NULL, *filename, *cache;
     int flags;
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
         goto out;
     }
 
-    /* Every driver supporting amendment must have create_opts */
-    assert(bs->drv->create_opts);
+    /* Every driver supporting amendment must have amend_opts */
+    assert(bs->drv->amend_opts);
 
-    create_opts = qemu_opts_append(create_opts, bs->drv->create_opts);
-    opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
+    amend_opts = qemu_opts_append(amend_opts, bs->drv->amend_opts);
+    opts = qemu_opts_create(amend_opts, NULL, 0, &error_abort);
     qemu_opts_do_parse(opts, options, NULL, &err);
     if (err) {
         error_report_err(err);
@@ -XXX,XX +XXX,XX @@ out:
 out_no_progress:
     blk_unref(blk);
     qemu_opts_del(opts);
-    qemu_opts_free(create_opts);
+    qemu_opts_free(amend_opts);
     g_free(options);
 
     if (ret) {
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

Some qcow2 create options can't be used for amend.
Remove them from the qcow2 create options and add generic logic to detect
such options in qemu-img

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
[mreitz: Dropped some iotests reference output hunks that became
         unnecessary thanks to
         "iotests: Make _filter_img_create more active"]
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-12-mreitz@redhat.com>
---
 block/qcow2.c              | 138 +++++++++-----------------------
 qemu-img.c                 |  18 ++++-
 tests/qemu-iotests/049.out | 102 ++++++++++++------------
 tests/qemu-iotests/061.out |  12 ++-
 tests/qemu-iotests/082.out | 158 ++++---------------------------------
 tests/qemu-iotests/085.out |  38 ++++-----
 tests/qemu-iotests/144.out |   4 +-
 tests/qemu-iotests/182.out |   2 +-
 tests/qemu-iotests/185.out |   8 +-
 tests/qemu-iotests/255.out |   8 +-
 tests/qemu-iotests/274.out |  46 +++++------
 tests/qemu-iotests/280.out |   2 +-
 12 files changed, 183 insertions(+), 353 deletions(-)

diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ static int qcow2_change_backing_file(BlockDriverState *bs,
     return qcow2_update_header(bs);
 }
 
-static int qcow2_crypt_method_from_format(const char *encryptfmt)
-{
-    if (g_str_equal(encryptfmt, "luks")) {
-        return QCOW_CRYPT_LUKS;
-    } else if (g_str_equal(encryptfmt, "aes")) {
-        return QCOW_CRYPT_AES;
-    } else {
-        return -EINVAL;
-    }
-}
-
 static int qcow2_set_up_encryption(BlockDriverState *bs,
                                    QCryptoBlockCreateOptions *cryptoopts,
                                    Error **errp)
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     bool lazy_refcounts = s->use_lazy_refcounts;
     bool data_file_raw = data_file_is_raw(bs);
     const char *compat = NULL;
-    uint64_t cluster_size = s->cluster_size;
-    bool encrypt;
-    int encformat;
     int refcount_bits = s->refcount_bits;
     int ret;
     QemuOptDesc *desc = opts->list->desc;
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
                 error_setg(errp, "Unknown compatibility level %s", compat);
                 return -EINVAL;
             }
-        } else if (!strcmp(desc->name, BLOCK_OPT_PREALLOC)) {
-            error_setg(errp, "Cannot change preallocation mode");
-            return -ENOTSUP;
         } else if (!strcmp(desc->name, BLOCK_OPT_SIZE)) {
             new_size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0);
         } else if (!strcmp(desc->name, BLOCK_OPT_BACKING_FILE)) {
             backing_file = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
         } else if (!strcmp(desc->name, BLOCK_OPT_BACKING_FMT)) {
             backing_format = qemu_opt_get(opts, BLOCK_OPT_BACKING_FMT);
-        } else if (!strcmp(desc->name, BLOCK_OPT_ENCRYPT)) {
-            encrypt = qemu_opt_get_bool(opts, BLOCK_OPT_ENCRYPT,
-                                        !!s->crypto);
-
-            if (encrypt != !!s->crypto) {
-                error_setg(errp,
-                           "Changing the encryption flag is not supported");
-                return -ENOTSUP;
-            }
-        } else if (!strcmp(desc->name, BLOCK_OPT_ENCRYPT_FORMAT)) {
-            encformat = qcow2_crypt_method_from_format(
-                qemu_opt_get(opts, BLOCK_OPT_ENCRYPT_FORMAT));
-
-            if (encformat != s->crypt_method_header) {
-                error_setg(errp,
-                           "Changing the encryption format is not supported");
-                return -ENOTSUP;
-            }
-        } else if (g_str_has_prefix(desc->name, "encrypt.")) {
-            error_setg(errp,
-                       "Changing the encryption parameters is not supported");
-            return -ENOTSUP;
-        } else if (!strcmp(desc->name, BLOCK_OPT_CLUSTER_SIZE)) {
-            cluster_size = qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE,
-                                             cluster_size);
-            if (cluster_size != s->cluster_size) {
-                error_setg(errp, "Changing the cluster size is not supported");
-                return -ENOTSUP;
-            }
         } else if (!strcmp(desc->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
             lazy_refcounts = qemu_opt_get_bool(opts, BLOCK_OPT_LAZY_REFCOUNTS,
                                                lazy_refcounts);
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
                                  "images");
                 return -EINVAL;
             }
-        } else if (!strcmp(desc->name, BLOCK_OPT_COMPRESSION_TYPE)) {
-            const char *ct_name =
-                qemu_opt_get(opts, BLOCK_OPT_COMPRESSION_TYPE);
-            int compression_type =
-                qapi_enum_parse(&Qcow2CompressionType_lookup, ct_name, -1,
-                                NULL);
-            if (compression_type == -1) {
-                error_setg(errp, "Unknown compression type: %s", ct_name);
-                return -ENOTSUP;
-            }
-
-            if (compression_type != s->compression_type) {
-                error_setg(errp, "Changing the compression type "
-                                 "is not supported");
-                return -ENOTSUP;
-            }
         } else {
             /* if this point is reached, this probably means a new option was
              * added without having it covered here */
@@ -XXX,XX +XXX,XX @@ void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
         .help = "The external data file must stay valid "           \
                 "as a raw image"                                    \
     },                                                              \
-    {                                                               \
-        .name = BLOCK_OPT_ENCRYPT,                                  \
-        .type = QEMU_OPT_BOOL,                                      \
-        .help = "Encrypt the image with format 'aes'. (Deprecated " \
-                "in favor of " BLOCK_OPT_ENCRYPT_FORMAT "=aes)",    \
-    },                                                              \
-    {                                                               \
-        .name = BLOCK_OPT_ENCRYPT_FORMAT,                           \
-        .type = QEMU_OPT_STRING,                                    \
-        .help = "Encrypt the image, format choices: 'aes', 'luks'", \
-    },                                                              \
-    BLOCK_CRYPTO_OPT_DEF_KEY_SECRET("encrypt.",                     \
-        "ID of secret providing qcow AES key or LUKS passphrase"),  \
-    BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_ALG("encrypt."),               \
-    BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_MODE("encrypt."),              \
-    BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_ALG("encrypt."),                \
-    BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_HASH_ALG("encrypt."),           \
-    BLOCK_CRYPTO_OPT_DEF_LUKS_HASH_ALG("encrypt."),                 \
-    BLOCK_CRYPTO_OPT_DEF_LUKS_ITER_TIME("encrypt."),                \
-    {                                                               \
-        .name = BLOCK_OPT_CLUSTER_SIZE,                             \
-        .type = QEMU_OPT_SIZE,                                      \
-        .help = "qcow2 cluster size",                               \
-        .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)            \
-    },                                                              \
-    {                                                               \
-        .name = BLOCK_OPT_PREALLOC,                                 \
-        .type = QEMU_OPT_STRING,                                    \
-        .help = "Preallocation mode (allowed values: off, "         \
-                "metadata, falloc, full)"                           \
-    },                                                              \
     {                                                               \
         .name = BLOCK_OPT_LAZY_REFCOUNTS,                           \
         .type = QEMU_OPT_BOOL,                                      \
@@ -XXX,XX +XXX,XX @@ void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
         .type = QEMU_OPT_NUMBER,                                    \
         .help = "Width of a reference count entry in bits",         \
         .def_value_str = "16"                                       \
-    },                                                              \
-    {                                                               \
-        .name = BLOCK_OPT_COMPRESSION_TYPE,                         \
-        .type = QEMU_OPT_STRING,                                    \
-        .help = "Compression method used for image cluster "        \
-                "compression",                                      \
-        .def_value_str = "zlib"                                     \
     }
 
 static QemuOptsList qcow2_create_opts = {
     .name = "qcow2-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(qcow2_create_opts.head),
     .desc = {
+        {                                                               \
+            .name = BLOCK_OPT_ENCRYPT,                                  \
+            .type = QEMU_OPT_BOOL,                                      \
+            .help = "Encrypt the image with format 'aes'. (Deprecated " \
+                    "in favor of " BLOCK_OPT_ENCRYPT_FORMAT "=aes)",    \
+        },                                                              \
+        {                                                               \
+            .name = BLOCK_OPT_ENCRYPT_FORMAT,                           \
+            .type = QEMU_OPT_STRING,                                    \
+            .help = "Encrypt the image, format choices: 'aes', 'luks'", \
+        },                                                              \
+        BLOCK_CRYPTO_OPT_DEF_KEY_SECRET("encrypt.",                     \
+            "ID of secret providing qcow AES key or LUKS passphrase"),  \
+        BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_ALG("encrypt."),               \
+        BLOCK_CRYPTO_OPT_DEF_LUKS_CIPHER_MODE("encrypt."),              \
+        BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_ALG("encrypt."),                \
+        BLOCK_CRYPTO_OPT_DEF_LUKS_IVGEN_HASH_ALG("encrypt."),           \
+        BLOCK_CRYPTO_OPT_DEF_LUKS_HASH_ALG("encrypt."),                 \
+        BLOCK_CRYPTO_OPT_DEF_LUKS_ITER_TIME("encrypt."),                \
+        {                                                               \
+            .name = BLOCK_OPT_CLUSTER_SIZE,                             \
+            .type = QEMU_OPT_SIZE,                                      \
+            .help = "qcow2 cluster size",                               \
+            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)            \
+        },                                                              \
+        {                                                               \
+            .name = BLOCK_OPT_PREALLOC,                                 \
+            .type = QEMU_OPT_STRING,                                    \
+            .help = "Preallocation mode (allowed values: off, "         \
+                    "metadata, falloc, full)"                           \
+        },                                                              \
+        {                                                               \
+            .name = BLOCK_OPT_COMPRESSION_TYPE,                         \
+            .type = QEMU_OPT_STRING,                                    \
+            .help = "Compression method used for image cluster "        \
+                    "compression",                                      \
+            .def_value_str = "zlib"                                     \
+        },
         QCOW_COMMON_OPTIONS,
         { /* end of list */ }
     }
diff --git a/qemu-img.c b/qemu-img.c
index XXXXXXX..XXXXXXX 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -XXX,XX +XXX,XX @@ static int print_amend_option_help(const char *format)
     /* Every driver supporting amendment must have amend_opts */
     assert(drv->amend_opts);
 
-    printf("Creation options for '%s':\n", format);
+    printf("Amend options for '%s':\n", format);
     qemu_opts_print_help(drv->amend_opts, false);
-    printf("\nNote that not all of these options may be amendable.\n");
     return 0;
 }
 
@@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv)
     amend_opts = qemu_opts_append(amend_opts, bs->drv->amend_opts);
     opts = qemu_opts_create(amend_opts, NULL, 0, &error_abort);
     qemu_opts_do_parse(opts, options, NULL, &err);
+
     if (err) {
+        /* Try to parse options using the create options */
+        Error *err1 = NULL;
+        amend_opts = qemu_opts_append(amend_opts, bs->drv->create_opts);
+        qemu_opts_del(opts);
+        opts = qemu_opts_create(amend_opts, NULL, 0, &error_abort);
+        qemu_opts_do_parse(opts, options, NULL, &err1);
+
+        if (!err1) {
+            error_append_hint(&err,
+                              "This option is only supported for image creation\n");
+        } else {
+            error_free(err1);
+        }
+
         error_report_err(err);
         ret = -1;
         goto out;
diff --git a/tests/qemu-iotests/049.out b/tests/qemu-iotests/049.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/049.out
+++ b/tests/qemu-iotests/049.out
@@ -XXX,XX +XXX,XX @@ QA output created by 049
 == 1. Traditional size parameter ==
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024b
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1k
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1K
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1048576 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1048576 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1G
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1073741824 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1073741824 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1T
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1099511627776 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1099511627776 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024.0
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024.0b
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5k
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1536 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5K
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1536 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1572864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1572864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5G
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1610612736 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1610612736 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5T
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1649267441664 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1649267441664 lazy_refcounts=off refcount_bits=16
 
 == 2. Specifying size via -o ==
 
 qemu-img create -f qcow2 -o size=1024 TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1024b TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1k TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1K TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1M TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1048576 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1048576 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1G TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1073741824 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1073741824 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1T TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1099511627776 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1099511627776 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1024.0 TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1024.0b TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1024 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1.5k TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1536 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1.5K TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1536 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1.5M TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1572864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1572864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1.5G TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1610612736 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1610612736 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o size=1.5T TEST_DIR/t.qcow2
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1649267441664 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1649267441664 lazy_refcounts=off refcount_bits=16
 
 == 3. Invalid sizes ==
 
@@ -XXX,XX +XXX,XX @@ qemu-img: TEST_DIR/t.qcow2: The image size must be specified only once
 == Check correct interpretation of suffixes for cluster size ==
 
 qemu-img create -f qcow2 -o cluster_size=1024 TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1024 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=1024b TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1024 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=1k TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1024 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=1K TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1024 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=1M TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1048576 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1048576 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=1024.0 TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1024 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=1024.0b TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=1024 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=0.5k TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=512 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=512 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=0.5K TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=512 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=512 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o cluster_size=0.5M TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=524288 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=524288 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 == Check compat level option ==
 
 qemu-img create -f qcow2 -o compat=0.10 TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=0.10 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o compat=1.1 TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=1.1 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o compat=0.42 TEST_DIR/t.qcow2 64M
 qemu-img: TEST_DIR/t.qcow2: Invalid parameter '0.42'
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.42 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=0.42 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o compat=foobar TEST_DIR/t.qcow2 64M
 qemu-img: TEST_DIR/t.qcow2: Invalid parameter 'foobar'
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=foobar cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=foobar lazy_refcounts=off refcount_bits=16
 
 == Check preallocation option ==
 
 qemu-img create -f qcow2 -o preallocation=off TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=off lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 preallocation=off compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o preallocation=metadata TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=metadata lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 preallocation=metadata compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o preallocation=1234 TEST_DIR/t.qcow2 64M
 qemu-img: TEST_DIR/t.qcow2: Invalid parameter '1234'
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=1234 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 preallocation=1234 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 == Check encryption option ==
 
 qemu-img create -f qcow2 -o encryption=off TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 encryption=off cluster_size=65536 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 --object secret,id=sec0,data=123456 -o encryption=on,encrypt.key-secret=sec0 TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 encryption=on encrypt.key-secret=sec0 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 encryption=on encrypt.key-secret=sec0 cluster_size=65536 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 == Check lazy_refcounts option (only with v3) ==
 
 qemu-img create -f qcow2 -o compat=1.1,lazy_refcounts=off TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=1.1 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o compat=1.1,lazy_refcounts=on TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=on refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=1.1 lazy_refcounts=on refcount_bits=16
 
 qemu-img create -f qcow2 -o compat=0.10,lazy_refcounts=off TEST_DIR/t.qcow2 64M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=0.10 lazy_refcounts=off refcount_bits=16
 
 qemu-img create -f qcow2 -o compat=0.10,lazy_refcounts=on TEST_DIR/t.qcow2 64M
 qemu-img: TEST_DIR/t.qcow2: Lazy refcounts only supported with compatibility level 1.1 and above (use version=v3 or greater)
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=on refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 compat=0.10 lazy_refcounts=on refcount_bits=16
 
 *** done
diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/061.out
+++ b/tests/qemu-iotests/061.out
@@ -XXX,XX +XXX,XX @@ qemu-img: Lazy refcounts only supported with compatibility level 1.1 and above (
 qemu-img: Lazy refcounts only supported with compatibility level 1.1 and above (use compat=1.1 or greater)
 qemu-img: Unknown compatibility level 0.42
 qemu-img: Invalid parameter 'foo'
-qemu-img: Changing the cluster size is not supported
-qemu-img: Changing the encryption flag is not supported
-qemu-img: Cannot change preallocation mode
+qemu-img: Invalid parameter 'cluster_size'
+This option is only supported for image creation
+qemu-img: Invalid parameter 'encryption'
+This option is only supported for image creation
+qemu-img: Invalid parameter 'preallocation'
+This option is only supported for image creation
 
 === Testing correct handling of unset value ===
 
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
 Should work:
 Should not work:
-qemu-img: Changing the cluster size is not supported
+qemu-img: Invalid parameter 'cluster_size'
+This option is only supported for image creation
 
 === Testing zero expansion on inactive clusters ===
 
diff --git a/tests/qemu-iotests/082.out b/tests/qemu-iotests/082.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/082.out
+++ b/tests/qemu-iotests/082.out
@@ -XXX,XX +XXX,XX @@ QA output created by 082
 === create: Options specified more than once ===
 
 Testing: create -f foo -f qcow2 TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 image: TEST_DIR/t.IMGFMT
 file format: IMGFMT
 virtual size: 128 MiB (134217728 bytes)
 cluster_size: 65536
 
 Testing: create -f qcow2 -o cluster_size=4k -o lazy_refcounts=on TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=4096 lazy_refcounts=on refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=4096 compression_type=zlib size=134217728 lazy_refcounts=on refcount_bits=16
 image: TEST_DIR/t.IMGFMT
 file format: IMGFMT
 virtual size: 128 MiB (134217728 bytes)
@@ -XXX,XX +XXX,XX @@ Format specific information:
     corrupt: false
 
 Testing: create -f qcow2 -o cluster_size=4k -o lazy_refcounts=on -o cluster_size=8k TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=8192 lazy_refcounts=on refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=8192 compression_type=zlib size=134217728 lazy_refcounts=on refcount_bits=16
 image: TEST_DIR/t.IMGFMT
 file format: IMGFMT
 virtual size: 128 MiB (134217728 bytes)
@@ -XXX,XX +XXX,XX @@ Format specific information:
     corrupt: false
 
 Testing: create -f qcow2 -o cluster_size=4k,cluster_size=8k TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=8192 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=8192 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 image: TEST_DIR/t.IMGFMT
 file format: IMGFMT
 virtual size: 128 MiB (134217728 bytes)
@@ -XXX,XX +XXX,XX @@ Supported options:
   size=<size>            - Virtual disk size
 
 Testing: create -f qcow2 -u -o backing_file=TEST_DIR/t.qcow2,,help TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,help cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2,,help lazy_refcounts=off refcount_bits=16
 
 Testing: create -f qcow2 -u -o backing_file=TEST_DIR/t.qcow2,,? TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,? cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2,,? lazy_refcounts=off refcount_bits=16
 
 Testing: create -f qcow2 -o backing_file=TEST_DIR/t.qcow2, -o help TEST_DIR/t.qcow2 128M
 qemu-img: Invalid option list: backing_file=TEST_DIR/t.qcow2,
@@ -XXX,XX +XXX,XX @@ qemu-img: Format driver 'bochs' does not support image creation
 === convert: Options specified more than once ===
 
 Testing: create -f qcow2 TEST_DIR/t.qcow2 128M
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 
 Testing: convert -f foo -f qcow2 TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base
 image: TEST_DIR/t.IMGFMT.base
@@ -XXX,XX +XXX,XX @@ cluster_size: 65536
 === amend: help for -o ===
 
 Testing: amend -f qcow2 -o help TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o ? TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o cluster_size=4k,help TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o cluster_size=4k,? TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o help,cluster_size=4k TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o ?,cluster_size=4k TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o cluster_size=4k -o help TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o cluster_size=4k -o ? TEST_DIR/t.qcow2
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -f qcow2 -o backing_file=TEST_DIR/t.qcow2,,help TEST_DIR/t.qcow2
 
 Testing: rebase -u -b  -f qcow2 TEST_DIR/t.qcow2
@@ -XXX,XX +XXX,XX @@ Testing: amend -f qcow2 -o backing_file=TEST_DIR/t.qcow2 -o ,, -o help TEST_DIR/
 qemu-img: Invalid option list: ,,
 
 Testing: amend -f qcow2 -o help
-Creation options for 'qcow2':
+Amend options for 'qcow2':
   backing_file=<str>     - File name of a base image
   backing_fmt=<str>      - Image format of the base image
-  cluster_size=<size>    - qcow2 cluster size
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
-  compression_type=<str> - Compression method used for image cluster compression
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
-  encrypt.cipher-alg=<str> - Name of encryption cipher algorithm
-  encrypt.cipher-mode=<str> - Name of encryption cipher mode
-  encrypt.format=<str>   - Encrypt the image, format choices: 'aes', 'luks'
-  encrypt.hash-alg=<str> - Name of encryption hash algorithm
-  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
-  encrypt.ivgen-alg=<str> - Name of IV generator algorithm
-  encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm
-  encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase
-  encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
-  preallocation=<str>    - Preallocation mode (allowed values: off, metadata, falloc, full)
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
 
-Note that not all of these options may be amendable.
-
 Testing: amend -o help
 qemu-img: Expecting one image file name
 
diff --git a/tests/qemu-iotests/085.out b/tests/qemu-iotests/085.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/085.out
+++ b/tests/qemu-iotests/085.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=134217728
 === Create a single snapshot on virtio0 ===
 
 { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', 'format': 'IMGFMT' } }
-Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2.1 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2.1 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Invalid command - missing device and nodename ===
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file
 === Create several transactional group snapshots ===
 
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/2-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/2-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/2-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/1-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/2-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2.2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/2-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/1-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/2-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2.2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/3-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/3-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/3-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/2-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/3-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/2-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/3-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/2-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/3-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/2-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/4-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/4-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/4-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/3-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/4-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/3-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/4-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/3-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/4-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/3-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/5-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/5-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/5-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/4-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/5-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/4-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/5-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/4-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/5-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/4-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/6-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/6-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/6-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/5-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/6-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/5-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/6-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/5-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/6-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/5-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/7-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/7-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/7-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/6-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/7-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/6-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/7-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/6-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/7-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/6-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/8-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/8-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/8-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/7-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/8-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/7-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/8-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/7-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/8-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/7-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/9-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/9-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/9-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/8-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/9-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/8-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/9-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/8-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/9-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/8-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/10-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/10-snapshot-v1.IMGFMT' } } ] } }
-Formatting 'TEST_DIR/10-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/9-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
-Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/9-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/10-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/9-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
+Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 backing_file=TEST_DIR/9-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Create a couple of snapshots using blockdev-snapshot ===
diff --git a/tests/qemu-iotests/144.out b/tests/qemu-iotests/144.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/144.out
+++ b/tests/qemu-iotests/144.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=536870912
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
 { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp.IMGFMT', 'format': 'IMGFMT' } }
-Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Performing block-commit on active layer ===
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/
 === Performing Live Snapshot 2 ===
 
 { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp2.IMGFMT', 'format': 'IMGFMT' } }
-Formatting 'TEST_DIR/tmp2.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/tmp2.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 *** done
diff --git a/tests/qemu-iotests/182.out b/tests/qemu-iotests/182.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/182.out
+++ b/tests/qemu-iotests/182.out
@@ -XXX,XX +XXX,XX @@ Is another process using the image [TEST_DIR/t.qcow2]?
 {'execute': 'blockdev-add', 'arguments': { 'node-name': 'node0', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } }
 {"return": {}}
 {'execute': 'blockdev-snapshot-sync', 'arguments': { 'node-name': 'node0', 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', 'snapshot-node-name': 'node1' } }
-Formatting 'TEST_DIR/t.qcow2.overlay', fmt=qcow2 size=197120 backing_file=TEST_DIR/t.qcow2 backing_fmt=file cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2.overlay', fmt=qcow2 cluster_size=65536 compression_type=zlib size=197120 backing_file=TEST_DIR/t.qcow2 backing_fmt=file lazy_refcounts=off refcount_bits=16
 {"return": {}}
 {'execute': 'blockdev-add', 'arguments': { 'node-name': 'node1', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } }
 {"return": {}}
diff --git a/tests/qemu-iotests/185.out b/tests/qemu-iotests/185.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/185.out
+++ b/tests/qemu-iotests/185.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
 === Creating backing chain ===
 
 { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT.mid', 'format': 'IMGFMT', 'mode': 'absolute-paths' } }
-Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 { 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write 0 4M"' } }
 wrote 4194304/4194304 bytes at offset 0
 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
 { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'absolute-paths' } }
-Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Start commit job and exit qemu ===
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.q
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
 { 'execute': 'drive-mirror', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } }
-Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 l
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
 { 'execute': 'drive-backup', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } }
-Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "disk"}}
diff --git a/tests/qemu-iotests/255.out b/tests/qemu-iotests/255.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/255.out
+++ b/tests/qemu-iotests/255.out
@@ -XXX,XX +XXX,XX @@ Finishing a commit job with background reads
 
 === Create backing chain and start VM ===
 
-Formatting 'TEST_DIR/PID-t.qcow2.mid', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-t.qcow2.mid', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-t.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 
 === Start background read requests ===
 
@@ -XXX,XX +XXX,XX @@ Closing the VM while a job is being cancelled
 
 === Create images and start VM ===
 
-Formatting 'TEST_DIR/PID-src.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-src.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-dst.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-dst.qcow2', fmt=qcow2 cluster_size=65536 compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16
 
 wrote 1048576/1048576 bytes at offset 0
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/274.out
+++ b/tests/qemu-iotests/274.out
@@ -XXX,XX +XXX,XX @@
 == Commit tests ==
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid lazy_refcounts=off refcount_bits=16
 
 wrote 2097152/2097152 bytes at offset 0
 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 === Testing HMP commit (top -> mid) ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid lazy_refcounts=off refcount_bits=16
 
 wrote 2097152/2097152 bytes at offset 0
 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 === Testing QMP active commit (top -> mid) ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid lazy_refcounts=off refcount_bits=16
 
 wrote 2097152/2097152 bytes at offset 0
 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576
 
 == Resize tests ==
 === preallocation=off ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=6442450944 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=6442450944 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=1073741824 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=1073741824 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 5368709120
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 5368709120
 { "start": 1073741824, "length": 7516192768, "depth": 0, "zero": true, "data": false}]
 
 === preallocation=metadata ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=34359738368 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=34359738368 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=32212254720 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=32212254720 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 33285996544
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 33285996544
 { "start": 34896609280, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 2685075456}]
 
 === preallocation=falloc ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=10485760 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=10485760 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=5242880 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=5242880 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 9437184
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 9437184
 { "start": 5242880, "length": 10485760, "depth": 0, "zero": false, "data": true, "offset": 327680}]
 
 === preallocation=full ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=16777216 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=8388608 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=8388608 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 11534336
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 11534336
 { "start": 8388608, "length": 4194304, "depth": 0, "zero": false, "data": true, "offset": 327680}]
 
 === preallocation=off ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=393216 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=259072 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=259072 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 259072
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 259072
 { "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}]
 
 === preallocation=off ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=409600 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=409600 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=262144 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 344064
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 344064
 { "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}]
 
 === preallocation=off ===
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=524288 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=524288 lazy_refcounts=off refcount_bits=16
 
-Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 compression_type=zlib size=262144 backing_file=TEST_DIR/PID-base lazy_refcounts=off refcount_bits=16
 
 wrote 65536/65536 bytes at offset 446464
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
diff --git a/tests/qemu-iotests/280.out b/tests/qemu-iotests/280.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/280.out
+++ b/tests/qemu-iotests/280.out
@@ -XXX,XX +XXX,XX @@
-Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib
+Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 
 === Launch VM ===
 Enabling migration QMP events on VM...
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

rename the write_func to create_write_func, and init_func to create_init_func.
This is preparation for other write_func that will be used to update the encryption keys.

No functional changes

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20200608094030.670121-7-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/crypto.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/block/crypto.c b/block/crypto.c
index XXXXXXX..XXXXXXX 100644
--- a/block/crypto.c
+++ b/block/crypto.c
@@ -XXX,XX +XXX,XX @@ struct BlockCryptoCreateData {
 };
 
 
-static ssize_t block_crypto_write_func(QCryptoBlock *block,
-                                       size_t offset,
-                                       const uint8_t *buf,
-                                       size_t buflen,
-                                       void *opaque,
-                                       Error **errp)
+static ssize_t block_crypto_create_write_func(QCryptoBlock *block,
+                                              size_t offset,
+                                              const uint8_t *buf,
+                                              size_t buflen,
+                                              void *opaque,
+                                              Error **errp)
 {
     struct BlockCryptoCreateData *data = opaque;
     ssize_t ret;
@@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_write_func(QCryptoBlock *block,
     return ret;
 }
 
-
-static ssize_t block_crypto_init_func(QCryptoBlock *block,
-                                      size_t headerlen,
-                                      void *opaque,
-                                      Error **errp)
+static ssize_t block_crypto_create_init_func(QCryptoBlock *block,
+                                             size_t headerlen,
+                                             void *opaque,
+                                             Error **errp)
 {
     struct BlockCryptoCreateData *data = opaque;
     Error *local_error = NULL;
@@ -XXX,XX +XXX,XX @@ static int block_crypto_co_create_generic(BlockDriverState *bs,
     };
 
     crypto = qcrypto_block_create(opts, NULL,
-                                  block_crypto_init_func,
-                                  block_crypto_write_func,
+                                  block_crypto_create_init_func,
+                                  block_crypto_create_write_func,
                                   &data,
                                   errp);
 
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

This implements the encryption key management using the generic code in
qcrypto layer and exposes it to the user via qemu-img

This code adds another 'write_func' because the initialization
write_func works directly on the underlying file, and amend
works on instance of luks device.

This commit also adds a 'hack/workaround' I and Kevin Wolf (thanks)
made to make the driver both support write sharing (to avoid breaking the users),
and be safe against concurrent  metadata update (the keyslots)

Eventually the write sharing for luks driver will be deprecated
and removed together with this hack.

The hack is that we ask (as a format driver) for BLK_PERM_CONSISTENT_READ
and then when we want to update the keys, we unshare that permission.
So if someone else has the image open, even readonly, encryption
key update will fail gracefully.

Also thanks to Daniel Berrange for the idea of
unsharing read, rather that write permission which allows
to avoid cases when the other user had opened the image read-only.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200608094030.670121-8-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/crypto.h |  34 +++++++++++++
 block/crypto.c | 130 +++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 161 insertions(+), 3 deletions(-)

diff --git a/block/crypto.h b/block/crypto.h
index XXXXXXX..XXXXXXX 100644
--- a/block/crypto.h
+++ b/block/crypto.h
@@ -XXX,XX +XXX,XX @@
 #define BLOCK_CRYPTO_OPT_LUKS_IVGEN_HASH_ALG "ivgen-hash-alg"
 #define BLOCK_CRYPTO_OPT_LUKS_HASH_ALG "hash-alg"
 #define BLOCK_CRYPTO_OPT_LUKS_ITER_TIME "iter-time"
+#define BLOCK_CRYPTO_OPT_LUKS_KEYSLOT "keyslot"
+#define BLOCK_CRYPTO_OPT_LUKS_STATE "state"
+#define BLOCK_CRYPTO_OPT_LUKS_OLD_SECRET "old-secret"
+#define BLOCK_CRYPTO_OPT_LUKS_NEW_SECRET "new-secret"
+
 
 #define BLOCK_CRYPTO_OPT_DEF_LUKS_KEY_SECRET(prefix)                    \
     BLOCK_CRYPTO_OPT_DEF_KEY_SECRET(prefix,                             \
@@ -XXX,XX +XXX,XX @@
         .help = "Time to spend in PBKDF in milliseconds",     \
     }
 
+#define BLOCK_CRYPTO_OPT_DEF_LUKS_STATE(prefix)                           \
+    {                                                                     \
+        .name = prefix BLOCK_CRYPTO_OPT_LUKS_STATE,                       \
+        .type = QEMU_OPT_STRING,                                          \
+        .help = "Select new state of affected keyslots (active/inactive)",\
+    }
+
+#define BLOCK_CRYPTO_OPT_DEF_LUKS_KEYSLOT(prefix)              \
+    {                                                          \
+        .name = prefix BLOCK_CRYPTO_OPT_LUKS_KEYSLOT,          \
+        .type = QEMU_OPT_NUMBER,                               \
+        .help = "Select a single keyslot to modify explicitly",\
+    }
+
+#define BLOCK_CRYPTO_OPT_DEF_LUKS_OLD_SECRET(prefix)            \
+    {                                                           \
+        .name = prefix BLOCK_CRYPTO_OPT_LUKS_OLD_SECRET,        \
+        .type = QEMU_OPT_STRING,                                \
+        .help = "Select all keyslots that match this password", \
+    }
+
+#define BLOCK_CRYPTO_OPT_DEF_LUKS_NEW_SECRET(prefix)            \
+    {                                                           \
+        .name = prefix BLOCK_CRYPTO_OPT_LUKS_NEW_SECRET,        \
+        .type = QEMU_OPT_STRING,                                \
+        .help = "New secret to set in the matching keyslots. "  \
+                "Empty string to erase",                        \
+    }
+
 QCryptoBlockCreateOptions *
 block_crypto_create_opts_init(QDict *opts, Error **errp);
 
diff --git a/block/crypto.c b/block/crypto.c
index XXXXXXX..XXXXXXX 100644
--- a/block/crypto.c
+++ b/block/crypto.c
@@ -XXX,XX +XXX,XX @@ typedef struct BlockCrypto BlockCrypto;
 
 struct BlockCrypto {
     QCryptoBlock *block;
+    bool updating_keys;
 };
 
 
@@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_read_func(QCryptoBlock *block,
     return ret;
 }
 
+static ssize_t block_crypto_write_func(QCryptoBlock *block,
+                                       size_t offset,
+                                       const uint8_t *buf,
+                                       size_t buflen,
+                                       void *opaque,
+                                       Error **errp)
+{
+    BlockDriverState *bs = opaque;
+    ssize_t ret;
+
+    ret = bdrv_pwrite(bs->file, offset, buf, buflen);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not write encryption header");
+        return ret;
+    }
+    return ret;
+}
+
 
 struct BlockCryptoCreateData {
     BlockBackend *blk;
@@ -XXX,XX +XXX,XX @@ static QemuOptsList block_crypto_create_opts_luks = {
 };
 
 
+static QemuOptsList block_crypto_amend_opts_luks = {
+    .name = "crypto",
+    .head = QTAILQ_HEAD_INITIALIZER(block_crypto_create_opts_luks.head),
+    .desc = {
+        BLOCK_CRYPTO_OPT_DEF_LUKS_STATE(""),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_KEYSLOT(""),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_OLD_SECRET(""),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_NEW_SECRET(""),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_ITER_TIME(""),
+        { /* end of list */ }
+    },
+};
+
 QCryptoBlockOpenOptions *
 block_crypto_open_opts_init(QDict *opts, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ block_crypto_get_specific_info_luks(BlockDriverState *bs, Error **errp)
     return spec_info;
 }
 
+static int
+block_crypto_amend_options_luks(BlockDriverState *bs,
+                                QemuOpts *opts,
+                                BlockDriverAmendStatusCB *status_cb,
+                                void *cb_opaque,
+                                bool force,
+                                Error **errp)
+{
+    BlockCrypto *crypto = bs->opaque;
+    QDict *cryptoopts = NULL;
+    QCryptoBlockAmendOptions *amend_options = NULL;
+    int ret;
+
+    assert(crypto);
+    assert(crypto->block);
+    crypto->updating_keys = true;
+
+    ret = bdrv_child_refresh_perms(bs, bs->file, errp);
+    if (ret < 0) {
+        goto cleanup;
+    }
+
+    cryptoopts = qemu_opts_to_qdict(opts, NULL);
+    qdict_put_str(cryptoopts, "format", "luks");
+    amend_options = block_crypto_amend_opts_init(cryptoopts, errp);
+    if (!amend_options) {
+        ret = -EINVAL;
+        goto cleanup;
+    }
+
+    ret = qcrypto_block_amend_options(crypto->block,
+                                      block_crypto_read_func,
+                                      block_crypto_write_func,
+                                      bs,
+                                      amend_options,
+                                      force,
+                                      errp);
+cleanup:
+    crypto->updating_keys = false;
+    bdrv_child_refresh_perms(bs, bs->file, errp);
+    qapi_free_QCryptoBlockAmendOptions(amend_options);
+    qobject_unref(cryptoopts);
+    return ret;
+}
+
+
+static void
+block_crypto_child_perms(BlockDriverState *bs, BdrvChild *c,
+                         const BdrvChildRole role,
+                         BlockReopenQueue *reopen_queue,
+                         uint64_t perm, uint64_t shared,
+                         uint64_t *nperm, uint64_t *nshared)
+{
+
+    BlockCrypto *crypto = bs->opaque;
+
+    bdrv_default_perms(bs, c, role, reopen_queue, perm, shared, nperm, nshared);
+
+    /*
+     * For backward compatibility, manually share the write
+     * and resize permission
+     */
+    *nshared |= (BLK_PERM_WRITE | BLK_PERM_RESIZE);
+    /*
+     * Since we are not fully a format driver, don't always request
+     * the read/resize permission but only when explicitly
+     * requested
+     */
+    *nperm &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
+    *nperm |= perm & (BLK_PERM_WRITE | BLK_PERM_RESIZE);
+
+    /*
+     * This driver doesn't modify LUKS metadata except
+     * when updating the encryption slots.
+     * Thus unlike a proper format driver we don't ask for
+     * shared write/read permission. However we need it
+     * when we are updating the keys, to ensure that only we
+     * have access to the device.
+     *
+     * Encryption update will set the crypto->updating_keys
+     * during that period and refresh permissions
+     *
+     */
+    if (crypto->updating_keys) {
+        /* need exclusive write access for header update */
+        *nperm |= BLK_PERM_WRITE;
+        /* unshare read and write permission */
+        *nshared &= ~(BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE);
+    }
+}
+
+
 static const char *const block_crypto_strong_runtime_opts[] = {
     BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET,
 
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_crypto_luks = {
     .bdrv_probe         = block_crypto_probe_luks,
     .bdrv_open          = block_crypto_open_luks,
     .bdrv_close         = block_crypto_close,
-    /* This driver doesn't modify LUKS metadata except when creating image.
-     * Allow share-rw=on as a special case. */
-    .bdrv_child_perm    = bdrv_default_perms,
+    .bdrv_child_perm    = block_crypto_child_perms,
     .bdrv_co_create     = block_crypto_co_create_luks,
     .bdrv_co_create_opts = block_crypto_co_create_opts_luks,
     .bdrv_co_truncate   = block_crypto_co_truncate,
     .create_opts        = &block_crypto_create_opts_luks,
+    .amend_opts         = &block_crypto_amend_opts_luks,
 
     .bdrv_reopen_prepare = block_crypto_reopen_prepare,
     .bdrv_refresh_limits = block_crypto_refresh_limits,
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_crypto_luks = {
     .bdrv_measure       = block_crypto_measure,
     .bdrv_get_info      = block_crypto_get_info_luks,
     .bdrv_get_specific_info = block_crypto_get_specific_info_luks,
+    .bdrv_amend_options = block_crypto_amend_options_luks,
 
     .is_format          = true,
 
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

Now that we have all the infrastructure in place,
wire it in the qcow2 driver and expose this to the user.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200608094030.670121-9-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/qcow2.c              | 71 +++++++++++++++++++++++++++++++++-----
 tests/qemu-iotests/082.out | 45 ++++++++++++++++++++++++
 2 files changed, 107 insertions(+), 9 deletions(-)

diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset,
     return ret;
 }
 
+static QDict*
+qcow2_extract_crypto_opts(QemuOpts *opts, const char *fmt, Error **errp)
+{
+    QDict *cryptoopts_qdict;
+    QDict *opts_qdict;
+
+    /* Extract "encrypt." options into a qdict */
+    opts_qdict = qemu_opts_to_qdict(opts, NULL);
+    qdict_extract_subqdict(opts_qdict, &cryptoopts_qdict, "encrypt.");
+    qobject_unref(opts_qdict);
+    qdict_put_str(cryptoopts_qdict, "format", fmt);
+    return cryptoopts_qdict;
+}
 
 /*
  * read qcow2 extension and fill bs
@@ -XXX,XX +XXX,XX @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs,
 
     if (has_luks) {
         g_autoptr(QCryptoBlockCreateOptions) create_opts = NULL;
-        QDict *opts_qdict;
-        QDict *cryptoopts;
+        QDict *cryptoopts = qcow2_extract_crypto_opts(opts, "luks", errp);
         size_t headerlen;
 
-        opts_qdict = qemu_opts_to_qdict(opts, NULL);
-        qdict_extract_subqdict(opts_qdict, &cryptoopts, "encrypt.");
-        qobject_unref(opts_qdict);
-
-        qdict_put_str(cryptoopts, "format", "luks");
-
         create_opts = block_crypto_create_opts_init(cryptoopts, errp);
         qobject_unref(cryptoopts);
         if (!create_opts) {
@@ -XXX,XX +XXX,XX @@ typedef enum Qcow2AmendOperation {
     QCOW2_NO_OPERATION = 0,
 
     QCOW2_UPGRADING,
+    QCOW2_UPDATING_ENCRYPTION,
     QCOW2_CHANGING_REFCOUNT_ORDER,
     QCOW2_DOWNGRADING,
 } Qcow2AmendOperation;
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     int ret;
     QemuOptDesc *desc = opts->list->desc;
     Qcow2AmendHelperCBInfo helper_cb_info;
+    bool encryption_update = false;
 
     while (desc && desc->name) {
         if (!qemu_opt_find(opts, desc->name)) {
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
             backing_file = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
         } else if (!strcmp(desc->name, BLOCK_OPT_BACKING_FMT)) {
             backing_format = qemu_opt_get(opts, BLOCK_OPT_BACKING_FMT);
+        } else if (g_str_has_prefix(desc->name, "encrypt.")) {
+            if (!s->crypto) {
+                error_setg(errp,
+                           "Can't amend encryption options - encryption not present");
+                return -EINVAL;
+            }
+            if (s->crypt_method_header != QCOW_CRYPT_LUKS) {
+                error_setg(errp,
+                           "Only LUKS encryption options can be amended");
+                return -ENOTSUP;
+            }
+            encryption_update = true;
         } else if (!strcmp(desc->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
             lazy_refcounts = qemu_opt_get_bool(opts, BLOCK_OPT_LAZY_REFCOUNTS,
                                                lazy_refcounts);
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
         .original_status_cb = status_cb,
         .original_cb_opaque = cb_opaque,
         .total_operations = (new_version != old_version)
-                          + (s->refcount_bits != refcount_bits)
+                          + (s->refcount_bits != refcount_bits) +
+                            (encryption_update == true)
     };
 
     /* Upgrade first (some features may require compat=1.1) */
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
         }
     }
 
+    if (encryption_update) {
+        QDict *amend_opts_dict;
+        QCryptoBlockAmendOptions *amend_opts;
+
+        helper_cb_info.current_operation = QCOW2_UPDATING_ENCRYPTION;
+        amend_opts_dict = qcow2_extract_crypto_opts(opts, "luks", errp);
+        if (!amend_opts_dict) {
+            return -EINVAL;
+        }
+        amend_opts = block_crypto_amend_opts_init(amend_opts_dict, errp);
+        qobject_unref(amend_opts_dict);
+        if (!amend_opts) {
+            return -EINVAL;
+        }
+        ret = qcrypto_block_amend_options(s->crypto,
+                                          qcow2_crypto_hdr_read_func,
+                                          qcow2_crypto_hdr_write_func,
+                                          bs,
+                                          amend_opts,
+                                          force,
+                                          errp);
+        qapi_free_QCryptoBlockAmendOptions(amend_opts);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     if (s->refcount_bits != refcount_bits) {
         int refcount_order = ctz32(refcount_bits);
 
@@ -XXX,XX +XXX,XX @@ static QemuOptsList qcow2_amend_opts = {
     .name = "qcow2-amend-opts",
     .head = QTAILQ_HEAD_INITIALIZER(qcow2_amend_opts.head),
     .desc = {
+        BLOCK_CRYPTO_OPT_DEF_LUKS_STATE("encrypt."),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_KEYSLOT("encrypt."),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_OLD_SECRET("encrypt."),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_NEW_SECRET("encrypt."),
+        BLOCK_CRYPTO_OPT_DEF_LUKS_ITER_TIME("encrypt."),
         QCOW_COMMON_OPTIONS,
         { /* end of list */ }
     }
diff --git a/tests/qemu-iotests/082.out b/tests/qemu-iotests/082.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/082.out
+++ b/tests/qemu-iotests/082.out
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
@@ -XXX,XX +XXX,XX @@ Amend options for 'qcow2':
   compat=<str>           - Compatibility level (v2 [0.10] or v3 [1.1])
   data_file=<str>        - File name of an external data file
   data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image
+  encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds
+  encrypt.keyslot=<num>  - Select a single keyslot to modify explicitly
+  encrypt.new-secret=<str> - New secret to set in the matching keyslots. Empty string to erase
+  encrypt.old-secret=<str> - Select all keyslots that match this password
+  encrypt.state=<str>    - Select new state of affected keyslots (active/inactive)
   lazy_refcounts=<bool (on/off)> - Postpone refcount updates
   refcount_bits=<num>    - Width of a reference count entry in bits
   size=<size>            - Virtual disk size
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

This commit adds two tests, which test the new amend interface
of both luks raw images and qcow2 luks encrypted images.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
[mreitz: Let 293 verify that LUKS works; drop $(seq) usage from 293;
         drop 293 and 294 from the auto group]
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-16-mreitz@redhat.com>
---
 tests/qemu-iotests/293     | 208 +++++++++++++++++++++++++++++++++++++
 tests/qemu-iotests/293.out |  99 ++++++++++++++++++
 tests/qemu-iotests/294     |  90 ++++++++++++++++
 tests/qemu-iotests/294.out |  30 ++++++
 tests/qemu-iotests/group   |   2 +
 5 files changed, 429 insertions(+)
 create mode 100755 tests/qemu-iotests/293
 create mode 100644 tests/qemu-iotests/293.out
 create mode 100755 tests/qemu-iotests/294
 create mode 100644 tests/qemu-iotests/294.out

diff --git a/tests/qemu-iotests/293 b/tests/qemu-iotests/293
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/293
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env bash
+#
+# Test encryption key management with luks
+# Based on 134
+#
+# Copyright (C) 2019 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=mlevitsk@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+status=1	# failure is the default!
+
+_cleanup()
+{
+	_cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt qcow2 luks
+_supported_proto file #TODO
+_require_working_luks
+
+QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT
+
+if [ "$IMGFMT" = "qcow2" ] ; then
+	PR="encrypt."
+	EXTRA_IMG_ARGS="-o encrypt.format=luks"
+fi
+
+
+# secrets: you are supposed to see the password as *******, see :-)
+S0="--object secret,id=sec0,data=hunter0"
+S1="--object secret,id=sec1,data=hunter1"
+S2="--object secret,id=sec2,data=hunter2"
+S3="--object secret,id=sec3,data=hunter3"
+S4="--object secret,id=sec4,data=hunter4"
+SECRETS="$S0 $S1 $S2 $S3 $S4"
+
+# image with given secret
+IMGS0="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,${PR}key-secret=sec0"
+IMGS1="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,${PR}key-secret=sec1"
+IMGS2="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,${PR}key-secret=sec2"
+IMGS3="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,${PR}key-secret=sec3"
+IMGS4="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,${PR}key-secret=sec4"
+
+
+echo "== creating a test image =="
+_make_test_img $S0 $EXTRA_IMG_ARGS -o ${PR}key-secret=sec0,${PR}iter-time=10 32M
+
+echo
+echo "== test that key 0 opens the image =="
+$QEMU_IO $S0 -c "read 0 4096" $IMGS0 | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== adding a password to slot 4 =="
+$QEMU_IMG amend $SECRETS $IMGS0 -o ${PR}state=active,${PR}new-secret=sec4,${PR}iter-time=10,${PR}keyslot=4
+echo "== adding a password to slot 1 =="
+$QEMU_IMG amend $SECRETS $IMGS0 -o ${PR}state=active,${PR}new-secret=sec1,${PR}iter-time=10
+echo "== adding a password to slot 3 =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=active,${PR}new-secret=sec3,${PR}iter-time=10,${PR}keyslot=3
+
+echo "== adding a password to slot 2 =="
+$QEMU_IMG amend $SECRETS $IMGS3 -o ${PR}state=active,${PR}new-secret=sec2,${PR}iter-time=10
+
+
+echo "== erase slot 4 =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}keyslot=4 | _filter_img_create
+
+
+echo
+echo "== all secrets should work =="
+for IMG in "$IMGS0" "$IMGS1" "$IMGS2" "$IMGS3"; do
+	$QEMU_IO $SECRETS -c "read 0 4096" $IMG | _filter_qemu_io | _filter_testdir
+done
+
+echo
+echo "== erase slot 0 and try it =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}old-secret=sec0 | _filter_img_create
+$QEMU_IO $SECRETS -c "read 0 4096" $IMGS0 | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== erase slot 2 and try it =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}keyslot=2 | _filter_img_create
+$QEMU_IO $SECRETS -c "read 0 4096" $IMGS2 | _filter_qemu_io | _filter_testdir
+
+
+# at this point slots 1 and 3 should be active
+
+echo
+echo "== filling  4 slots with secret 2 =="
+for ((i = 0; i < 4; i++)); do
+	$QEMU_IMG amend $SECRETS $IMGS3 -o ${PR}state=active,${PR}new-secret=sec2,${PR}iter-time=10
+done
+
+echo
+echo "== adding secret 0 =="
+	$QEMU_IMG amend $SECRETS $IMGS3 -o ${PR}state=active,${PR}new-secret=sec0,${PR}iter-time=10
+
+echo
+echo "== adding secret 3 (last slot) =="
+	$QEMU_IMG amend $SECRETS $IMGS3 -o ${PR}state=active,${PR}new-secret=sec3,${PR}iter-time=10
+
+echo
+echo "== trying to add another slot (should fail) =="
+$QEMU_IMG amend $SECRETS $IMGS2 -o ${PR}state=active,${PR}new-secret=sec3,${PR}iter-time=10
+
+echo
+echo "== all secrets should work again =="
+for IMG in "$IMGS0" "$IMGS1" "$IMGS2" "$IMGS3"; do
+	$QEMU_IO $SECRETS -c "read 0 4096" $IMG | _filter_qemu_io | _filter_testdir
+done
+
+
+echo
+
+echo "== erase all keys of secret 2=="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}old-secret=sec2
+
+echo "== erase all keys of secret 1=="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}old-secret=sec1
+
+echo "== erase all keys of secret 0=="
+$QEMU_IMG amend $SECRETS $IMGS0 -o ${PR}state=inactive,${PR}old-secret=sec0
+
+echo "== erasing secret3 will fail now since it is the only secret (in 3 slots) =="
+$QEMU_IMG amend $SECRETS $IMGS3 -o ${PR}state=inactive,${PR}old-secret=sec3
+
+echo
+echo "== only secret3 should work now  =="
+for IMG in "$IMGS0" "$IMGS1" "$IMGS2" "$IMGS3"; do
+	$QEMU_IO $SECRETS -c "read 0 4096" $IMG | _filter_qemu_io | _filter_testdir
+done
+
+echo
+echo "== add secret0  =="
+$QEMU_IMG amend $SECRETS $IMGS3 -o ${PR}state=active,${PR}new-secret=sec0,${PR}iter-time=10
+
+echo "== erase secret3 =="
+$QEMU_IMG amend $SECRETS $IMGS0 -o ${PR}state=inactive,${PR}old-secret=sec3
+
+echo
+echo "== only secret0 should work now  =="
+for IMG in "$IMGS0" "$IMGS1" "$IMGS2" "$IMGS3"; do
+	$QEMU_IO $SECRETS -c "read 0 4096" $IMG | _filter_qemu_io | _filter_testdir
+done
+
+echo
+echo "== replace secret0 with secret1 (should fail)  =="
+$QEMU_IMG amend $SECRETS $IMGS0 -o ${PR}state=active,${PR}new-secret=sec1,${PR}keyslot=0
+
+echo
+echo "== replace secret0 with secret1 with force (should work)  =="
+$QEMU_IMG amend $SECRETS $IMGS0 -o ${PR}state=active,${PR}new-secret=sec1,${PR}iter-time=10,${PR}keyslot=0 --force
+
+echo
+echo "== only secret1 should work now  =="
+for IMG in "$IMGS0" "$IMGS1" "$IMGS2" "$IMGS3"; do
+	$QEMU_IO $SECRETS -c "read 0 4096" $IMG | _filter_qemu_io | _filter_testdir
+done
+
+
+echo
+echo "== erase last secret (should fail)  =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}keyslot=0
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}old-secret=sec1
+
+
+echo "== erase non existing secrets (should fail)  =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}old-secret=sec5 --force
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}old-secret=sec0 --force
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}keyslot=1 --force
+
+echo
+echo "== erase last secret with force by slot (should work)  =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o ${PR}state=inactive,${PR}keyslot=0 --force
+
+echo
+echo "== we have no secrets now, data is lost forever =="
+for IMG in "$IMGS0" "$IMGS1" "$IMGS2" "$IMGS3"; do
+	$QEMU_IO $SECRETS -c "read 0 4096" $IMG | _filter_qemu_io | _filter_testdir
+done
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
+
diff --git a/tests/qemu-iotests/293.out b/tests/qemu-iotests/293.out
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/293.out
@@ -XXX,XX +XXX,XX @@
+QA output created by 293
+== creating a test image ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33554432
+
+== test that key 0 opens the image ==
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== adding a password to slot 4 ==
+== adding a password to slot 1 ==
+== adding a password to slot 3 ==
+== adding a password to slot 2 ==
+== erase slot 4 ==
+
+== all secrets should work ==
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== erase slot 0 and try it ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+
+== erase slot 2 and try it ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+
+== filling  4 slots with secret 2 ==
+
+== adding secret 0 ==
+
+== adding secret 3 (last slot) ==
+
+== trying to add another slot (should fail) ==
+qemu-img: Can't add a keyslot - all keyslots are in use
+
+== all secrets should work again ==
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== erase all keys of secret 2==
+== erase all keys of secret 1==
+== erase all keys of secret 0==
+== erasing secret3 will fail now since it is the only secret (in 3 slots) ==
+qemu-img: All the active keyslots match the (old) password that was given and erasing them will erase all the data in the image irreversibly - refusing operation
+
+== only secret3 should work now  ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== add secret0  ==
+== erase secret3 ==
+
+== only secret0 should work now  ==
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+
+== replace secret0 with secret1 (should fail)  ==
+qemu-img: Refusing to overwrite active keyslot 0 - please erase it first
+
+== replace secret0 with secret1 with force (should work)  ==
+
+== only secret1 should work now  ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+
+== erase last secret (should fail)  ==
+qemu-img: Attempt to erase the only active keyslot 0 which will erase all the data in the image irreversibly - refusing operation
+qemu-img: All the active keyslots match the (old) password that was given and erasing them will erase all the data in the image irreversibly - refusing operation
+== erase non existing secrets (should fail)  ==
+qemu-img: No secret with id 'sec5'
+qemu-img: No keyslots match given (old) password for erase operation
+
+== erase last secret with force by slot (should work)  ==
+
+== we have no secrets now, data is lost forever ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+*** done
diff --git a/tests/qemu-iotests/294 b/tests/qemu-iotests/294
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/294
@@ -XXX,XX +XXX,XX @@
+#
+# Copyright (C) 2019 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=mlevitsk@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+status=1	# failure is the default!
+
+_cleanup()
+{
+	_cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt luks
+_supported_proto file #TODO
+
+QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT
+
+# you are supposed to see the password as *******, see :-)
+S0="--object secret,id=sec0,data=hunter0"
+S1="--object secret,id=sec1,data=hunter1"
+SECRETS="$S0 $S1"
+
+
+IMGS0="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,key-secret=sec0"
+IMGS1="--image-opts driver=$IMGFMT,file.filename=$TEST_IMG,key-secret=sec1"
+
+echo "== creating a test image =="
+_make_test_img $S0 -o "key-secret=sec0,iter-time=10" 32M
+
+echo
+echo "== test that key 0 opens the image =="
+$QEMU_IO $S0 -c "read 0 4096" $IMGS0 | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== adding a password to slot 1 =="
+$QEMU_IMG amend $SECRETS $IMGS0 -o state=active,new-secret=sec1,keyslot=1,iter-time=10
+
+echo
+echo "== 'backup' the image header =="
+dd if=$TEST_IMG_FILE of=${TEST_IMG_FILE}.bk bs=4K skip=0 count=1
+
+echo
+echo "== erase slot 0 =="
+$QEMU_IMG amend $SECRETS $IMGS1 -o state=inactive,keyslot=0 | _filter_img_create
+
+echo
+echo "== test that key 0 doesn't open the image =="
+$QEMU_IO $S0 -c "read 0 4096" $IMGS0 | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== 'restore' the image header =="
+dd if=${TEST_IMG_FILE}.bk of=${TEST_IMG_FILE} bs=4K skip=0 count=1 conv=notrunc
+
+echo
+echo "== test that key 0 still doesn't open the image (key material is erased) =="
+$QEMU_IO $SECRETS -c "read 0 4096" $IMGS0 | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== test that key 1 still works =="
+$QEMU_IO $SECRETS -c "read 0 4096" $IMGS1 | _filter_qemu_io | _filter_testdir
+
+echo "*** done"
+rm -f $seq.full
+status=0
+
+
+exit 0
diff --git a/tests/qemu-iotests/294.out b/tests/qemu-iotests/294.out
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/294.out
@@ -XXX,XX +XXX,XX @@
+QA output created by 294
+== creating a test image ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33554432
+
+== test that key 0 opens the image ==
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== adding a password to slot 1 ==
+
+== 'backup' the image header ==
+1+0 records in
+1+0 records out
+
+== erase slot 0 ==
+
+== test that key 0 doesn't open the image ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+
+== 'restore' the image header ==
+1+0 records in
+1+0 records out
+
+== test that key 0 still doesn't open the image (key material is erased) ==
+qemu-io: can't open: Invalid password, cannot unlock any keyslot
+
+== test that key 1 still works ==
+read 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+*** done
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -XXX,XX +XXX,XX @@
 290 rw auto quick
 291 rw quick
 292 rw auto quick
+293 rw
+294 rw quick
 297 meta
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

blockdev-amend will be used similiar to blockdev-create
to allow on the fly changes of the structure of the format based block devices.

Current plan is to first support encryption keyslot management for luks
based formats (raw and embedded in qcow2)

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20200608094030.670121-12-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qapi/block-core.json      |  42 ++++++++++++++
 qapi/job.json             |   4 +-
 include/block/block_int.h |  21 +++++--
 block/amend.c             | 113 ++++++++++++++++++++++++++++++++++++++
 block/Makefile.objs       |   2 +-
 5 files changed, 174 insertions(+), 8 deletions(-)
 create mode 100644 block/amend.c

diff --git a/qapi/block-core.json b/qapi/block-core.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -XXX,XX +XXX,XX @@
   'data': { 'job-id': 'str',
             'options': 'BlockdevCreateOptions' } }
 
+##
+# @BlockdevAmendOptions:
+#
+# Options for amending an image format
+#
+# @driver:          Block driver of the node to amend.
+#
+# Since: 5.1
+##
+{ 'union': 'BlockdevAmendOptions',
+  'base': {
+      'driver':         'BlockdevDriver' },
+  'discriminator': 'driver',
+  'data': {
+  } }
+
+##
+# @x-blockdev-amend:
+#
+# Starts a job to amend format specific options of an existing open block device
+# The job is automatically finalized, but a manual job-dismiss is required.
+#
+# @job-id:          Identifier for the newly created job.
+#
+# @node-name:       Name of the block node to work on
+#
+# @options:         Options (driver specific)
+#
+# @force:           Allow unsafe operations, format specific
+#                   For luks that allows erase of the last active keyslot
+#                   (permanent loss of data),
+#                   and replacement of an active keyslot
+#                   (possible loss of data if IO error happens)
+#
+# Since: 5.1
+##
+{ 'command': 'x-blockdev-amend',
+  'data': { 'job-id': 'str',
+            'node-name': 'str',
+            'options': 'BlockdevAmendOptions',
+            '*force': 'bool' } }
+
 ##
 # @BlockErrorAction:
 #
diff --git a/qapi/job.json b/qapi/job.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/job.json
+++ b/qapi/job.json
@@ -XXX,XX +XXX,XX @@
 #
 # @create: image creation job type, see "blockdev-create" (since 3.0)
 #
+# @amend: image options amend job type, see "x-blockdev-amend" (since 5.1)
+#
 # Since: 1.7
 ##
 { 'enum': 'JobType',
-  'data': ['commit', 'stream', 'mirror', 'backup', 'create'] }
+  'data': ['commit', 'stream', 'mirror', 'backup', 'create', 'amend'] }
 
 ##
 # @JobStatus:
diff --git a/include/block/block_int.h b/include/block/block_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -XXX,XX +XXX,XX @@ struct BlockDriver {
     int (*bdrv_file_open)(BlockDriverState *bs, QDict *options, int flags,
                           Error **errp);
     void (*bdrv_close)(BlockDriverState *bs);
+
+
     int coroutine_fn (*bdrv_co_create)(BlockdevCreateOptions *opts,
                                        Error **errp);
     int coroutine_fn (*bdrv_co_create_opts)(BlockDriver *drv,
                                             const char *filename,
                                             QemuOpts *opts,
                                             Error **errp);
+
+    int coroutine_fn (*bdrv_co_amend)(BlockDriverState *bs,
+                                      BlockdevAmendOptions *opts,
+                                      bool force,
+                                      Error **errp);
+
+    int (*bdrv_amend_options)(BlockDriverState *bs,
+                              QemuOpts *opts,
+                              BlockDriverAmendStatusCB *status_cb,
+                              void *cb_opaque,
+                              bool force,
+                              Error **errp);
+
     int (*bdrv_make_empty)(BlockDriverState *bs);
 
     /*
@@ -XXX,XX +XXX,XX @@ struct BlockDriver {
                                       BdrvCheckResult *result,
                                       BdrvCheckMode fix);
 
-    int (*bdrv_amend_options)(BlockDriverState *bs, QemuOpts *opts,
-                              BlockDriverAmendStatusCB *status_cb,
-                              void *cb_opaque,
-                              bool force,
-                              Error **errp);
-
     void (*bdrv_debug_event)(BlockDriverState *bs, BlkdebugEvent event);
 
     /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
diff --git a/block/amend.c b/block/amend.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/block/amend.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Block layer code related to image options amend
+ *
+ * Copyright (c) 2018 Kevin Wolf <kwolf@redhat.com>
+ * Copyright (c) 2020 Red Hat. Inc
+ *
+ * Heavily based on create.c
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "block/block_int.h"
+#include "qemu/job.h"
+#include "qemu/main-loop.h"
+#include "qapi/qapi-commands-block-core.h"
+#include "qapi/qapi-visit-block-core.h"
+#include "qapi/clone-visitor.h"
+#include "qapi/error.h"
+
+typedef struct BlockdevAmendJob {
+    Job common;
+    BlockdevAmendOptions *opts;
+    BlockDriverState *bs;
+    bool force;
+} BlockdevAmendJob;
+
+static int coroutine_fn blockdev_amend_run(Job *job, Error **errp)
+{
+    BlockdevAmendJob *s = container_of(job, BlockdevAmendJob, common);
+    int ret;
+
+    job_progress_set_remaining(&s->common, 1);
+    ret = s->bs->drv->bdrv_co_amend(s->bs, s->opts, s->force, errp);
+    job_progress_update(&s->common, 1);
+    qapi_free_BlockdevAmendOptions(s->opts);
+    return ret;
+}
+
+static const JobDriver blockdev_amend_job_driver = {
+    .instance_size = sizeof(BlockdevAmendJob),
+    .job_type      = JOB_TYPE_AMEND,
+    .run           = blockdev_amend_run,
+};
+
+void qmp_x_blockdev_amend(const char *job_id,
+                          const char *node_name,
+                          BlockdevAmendOptions *options,
+                          bool has_force,
+                          bool force,
+                          Error **errp)
+{
+    BlockdevAmendJob *s;
+    const char *fmt = BlockdevDriver_str(options->driver);
+    BlockDriver *drv = bdrv_find_format(fmt);
+    BlockDriverState *bs = bdrv_find_node(node_name);
+
+
+    if (!drv) {
+        error_setg(errp, "Block driver '%s' not found or not supported", fmt);
+        return;
+    }
+
+    /*
+     * If the driver is in the schema, we know that it exists. But it may not
+     * be whitelisted.
+     */
+    if (bdrv_uses_whitelist() && !bdrv_is_whitelisted(drv, false)) {
+        error_setg(errp, "Driver is not whitelisted");
+        return;
+    }
+
+    if (bs->drv != drv) {
+        error_setg(errp,
+                   "x-blockdev-amend doesn't support changing the block driver");
+        return;
+    }
+
+    /* Error out if the driver doesn't support .bdrv_co_amend */
+    if (!drv->bdrv_co_amend) {
+        error_setg(errp, "Driver does not support x-blockdev-amend");
+        return;
+    }
+
+    /* Create the block job */
+    s = job_create(job_id, &blockdev_amend_job_driver, NULL,
+                   bdrv_get_aio_context(bs), JOB_DEFAULT | JOB_MANUAL_DISMISS,
+                   NULL, NULL, errp);
+    if (!s) {
+        return;
+    }
+
+    s->bs = bs,
+    s->opts = QAPI_CLONE(BlockdevAmendOptions, options),
+    s->force = has_force ? force : false;
+    job_start(&s->common);
+}
diff --git a/block/Makefile.objs b/block/Makefile.objs
index XXXXXXX..XXXXXXX 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -XXX,XX +XXX,XX @@ block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += file-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 block-obj-$(CONFIG_LINUX_IO_URING) += io_uring.o
-block-obj-y += null.o mirror.o commit.o io.o create.o
+block-obj-y += null.o mirror.o commit.o io.o create.o amend.o
 block-obj-y += throttle-groups.o
 block-obj-$(CONFIG_LINUX) += nvme.o
 
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200608094030.670121-13-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qapi/block-core.json | 14 ++++++++-
 block/crypto.c       | 72 ++++++++++++++++++++++++++++++++------------
 2 files changed, 66 insertions(+), 20 deletions(-)

From: Maxim Levitsky <mlevitsk@redhat.com>

Currently the implementation only supports amending the encryption
options, unlike the qemu-img version

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200608094030.670121-14-mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qapi/block-core.json | 16 +++++++++++++++-
 block/qcow2.c        | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/qapi/block-core.json b/qapi/block-core.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -XXX,XX +XXX,XX @@
   'data': { }
 }
 
+##
+# @BlockdevAmendOptionsQcow2:
+#
+# Driver specific image amend options for qcow2.
+# For now, only encryption options can be amended
+#
+# @encrypt          Encryption options to be amended
+#
+# Since: 5.1
+##
+{ 'struct': 'BlockdevAmendOptionsQcow2',
+  'data': { '*encrypt':         'QCryptoBlockAmendOptions' } }
+
 ##
 # @BlockdevAmendOptions:
 #
@@ -XXX,XX +XXX,XX @@
       'driver':         'BlockdevDriver' },
   'discriminator': 'driver',
   'data': {
-      'luks':           'BlockdevAmendOptionsLUKS' } }
+      'luks':           'BlockdevAmendOptionsLUKS',
+      'qcow2':          'BlockdevAmendOptionsQcow2' } }
 
 ##
 # @x-blockdev-amend:
diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     return 0;
 }
 
+static int coroutine_fn qcow2_co_amend(BlockDriverState *bs,
+                                       BlockdevAmendOptions *opts,
+                                       bool force,
+                                       Error **errp)
+{
+    BlockdevAmendOptionsQcow2 *qopts = &opts->u.qcow2;
+    BDRVQcow2State *s = bs->opaque;
+    int ret = 0;
+
+    if (qopts->has_encrypt) {
+        if (!s->crypto) {
+            error_setg(errp, "image is not encrypted, can't amend");
+            return -EOPNOTSUPP;
+        }
+
+        if (qopts->encrypt->format != Q_CRYPTO_BLOCK_FORMAT_LUKS) {
+            error_setg(errp,
+                       "Amend can't be used to change the qcow2 encryption format");
+            return -EOPNOTSUPP;
+        }
+
+        if (s->crypt_method_header != QCOW_CRYPT_LUKS) {
+            error_setg(errp,
+                       "Only LUKS encryption options can be amended for qcow2 with blockdev-amend");
+            return -EOPNOTSUPP;
+        }
+
+        ret = qcrypto_block_amend_options(s->crypto,
+                                          qcow2_crypto_hdr_read_func,
+                                          qcow2_crypto_hdr_write_func,
+                                          bs,
+                                          qopts->encrypt,
+                                          force,
+                                          errp);
+    }
+    return ret;
+}
+
 /*
  * If offset or size are negative, respectively, they will not be included in
  * the BLOCK_IMAGE_CORRUPTED event emitted.
@@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_qcow2 = {
     .mutable_opts        = mutable_opts,
     .bdrv_co_check       = qcow2_co_check,
     .bdrv_amend_options  = qcow2_amend_options,
+    .bdrv_co_amend       = qcow2_co_amend,
 
     .bdrv_detach_aio_context  = qcow2_detach_aio_context,
     .bdrv_attach_aio_context  = qcow2_attach_aio_context,
-- 
2.26.2

From: Maxim Levitsky <mlevitsk@redhat.com>

This commit adds two tests that cover the
new blockdev-amend functionality of luks and qcow2 driver

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
[mreitz: Let 295 verify that LUKS works; drop 295 and 296 from the auto
         group]
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200625125548.870061-20-mreitz@redhat.com>
---
 tests/qemu-iotests/295     | 280 +++++++++++++++++++++++++++++++++++++
 tests/qemu-iotests/295.out |  40 ++++++
 tests/qemu-iotests/296     | 234 +++++++++++++++++++++++++++++++
 tests/qemu-iotests/296.out |  33 +++++
 tests/qemu-iotests/group   |   2 +
 5 files changed, 589 insertions(+)
 create mode 100755 tests/qemu-iotests/295
 create mode 100644 tests/qemu-iotests/295.out
 create mode 100755 tests/qemu-iotests/296
 create mode 100644 tests/qemu-iotests/296.out

diff --git a/tests/qemu-iotests/295 b/tests/qemu-iotests/295
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/295
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Test case QMP's encrypted key management
+#
+# Copyright (C) 2019 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+import iotests
+import os
+import time
+import json
+
+test_img = os.path.join(iotests.test_dir, 'test.img')
+
+class Secret:
+    def __init__(self, index):
+        self._id = "keysec" + str(index)
+        # you are not supposed to see the password...
+        self._secret = "hunter" + str(index)
+
+    def id(self):
+        return self._id
+
+    def secret(self):
+        return self._secret
+
+    def to_cmdline_object(self):
+        return  [ "secret,id=" + self._id + ",data=" + self._secret]
+
+    def to_qmp_object(self):
+        return { "qom_type" : "secret", "id": self.id(),
+                 "props": { "data": self.secret() } }
+
+################################################################################
+class EncryptionSetupTestCase(iotests.QMPTestCase):
+
+    # test case startup
+    def setUp(self):
+        # start the VM
+        self.vm = iotests.VM()
+        self.vm.launch()
+
+        # create the secrets and load 'em into the VM
+        self.secrets = [ Secret(i) for i in range(0, 6) ]
+        for secret in self.secrets:
+            result = self.vm.qmp("object-add", **secret.to_qmp_object())
+            self.assert_qmp(result, 'return', {})
+
+        if iotests.imgfmt == "qcow2":
+            self.pfx = "encrypt."
+            self.img_opts = [ '-o', "encrypt.format=luks" ]
+        else:
+            self.pfx = ""
+            self.img_opts = []
+
+    # test case shutdown
+    def tearDown(self):
+        # stop the VM
+        self.vm.shutdown()
+
+    ###########################################################################
+    # create the encrypted block device
+    def createImg(self, file, secret):
+
+        iotests.qemu_img(
+            'create',
+            '--object', *secret.to_cmdline_object(),
+            '-f', iotests.imgfmt,
+            '-o', self.pfx + 'key-secret=' + secret.id(),
+            '-o', self.pfx + 'iter-time=10',
+            *self.img_opts,
+            file,
+            '1M')
+
+    ###########################################################################
+    # open an encrypted block device
+    def openImageQmp(self, id, file, secret, read_only = False):
+
+        encrypt_options = {
+            'key-secret' : secret.id()
+        }
+
+        if iotests.imgfmt == "qcow2":
+            encrypt_options = {
+                'encrypt': {
+                    'format':'luks',
+                    **encrypt_options
+                }
+            }
+
+        result = self.vm.qmp('blockdev-add', **
+            {
+                'driver': iotests.imgfmt,
+                'node-name': id,
+                'read-only': read_only,
+
+                **encrypt_options,
+
+                'file': {
+                    'driver': 'file',
+                    'filename': test_img,
+                }
+            }
+        )
+        self.assert_qmp(result, 'return', {})
+
+    # close the encrypted block device
+    def closeImageQmp(self, id):
+        result = self.vm.qmp('blockdev-del', **{ 'node-name': id })
+        self.assert_qmp(result, 'return', {})
+
+    ###########################################################################
+    # add a key to an encrypted block device
+    def addKeyQmp(self, id, new_secret, secret = None,
+                  slot = None, force = False):
+
+        crypt_options = {
+            'state'      : 'active',
+            'new-secret' : new_secret.id(),
+            'iter-time' : 10
+        }
+
+        if slot != None:
+            crypt_options['keyslot'] = slot
+
+
+        if secret != None:
+            crypt_options['secret'] = secret.id()
+
+        if iotests.imgfmt == "qcow2":
+            crypt_options['format'] = 'luks'
+            crypt_options = {
+                'encrypt': crypt_options
+            }
+
+        args = {
+            'node-name': id,
+            'job-id' : 'job_add_key',
+            'options' : {
+                    'driver' : iotests.imgfmt,
+                    **crypt_options
+                },
+        }
+
+        if force == True:
+            args['force'] = True
+
+        #TODO: check what jobs return
+        result = self.vm.qmp('x-blockdev-amend', **args)
+        assert result['return'] == {}
+        self.vm.run_job('job_add_key')
+
+    # erase a key from an encrypted block device
+    def eraseKeyQmp(self, id, old_secret = None, slot = None, force = False):
+
+        crypt_options = {
+            'state'      : 'inactive',
+        }
+
+        if slot != None:
+            crypt_options['keyslot'] = slot
+        if old_secret != None:
+            crypt_options['old-secret'] = old_secret.id()
+
+        if iotests.imgfmt == "qcow2":
+            crypt_options['format'] = 'luks'
+            crypt_options = {
+                'encrypt': crypt_options
+            }
+
+        args = {
+            'node-name': id,
+            'job-id' : 'job_erase_key',
+            'options' : {
+                    'driver' : iotests.imgfmt,
+                    **crypt_options
+                },
+        }
+
+        if force == True:
+            args['force'] = True
+
+        result = self.vm.qmp('x-blockdev-amend', **args)
+        assert result['return'] == {}
+        self.vm.run_job('job_erase_key')
+
+    ###########################################################################
+    # create image, and change its key
+    def testChangeKey(self):
+
+        # create the image with secret0 and open it
+        self.createImg(test_img, self.secrets[0]);
+        self.openImageQmp("testdev", test_img, self.secrets[0])
+
+        # add key to slot 1
+        self.addKeyQmp("testdev", new_secret = self.secrets[1])
+
+        # add key to slot 5
+        self.addKeyQmp("testdev", new_secret = self.secrets[2], slot=5)
+
+        # erase key from slot 0
+        self.eraseKeyQmp("testdev", old_secret = self.secrets[0])
+
+        #reopen the image with secret1
+        self.closeImageQmp("testdev")
+        self.openImageQmp("testdev", test_img, self.secrets[1])
+
+        # close and erase the image for good
+        self.closeImageQmp("testdev")
+        os.remove(test_img)
+
+    # test that if we erase the old password,
+    # we can still change the encryption keys using 'old-secret'
+    def testOldPassword(self):
+
+        # create the image with secret0 and open it
+        self.createImg(test_img, self.secrets[0]);
+        self.openImageQmp("testdev", test_img, self.secrets[0])
+
+        # add key to slot 1
+        self.addKeyQmp("testdev", new_secret = self.secrets[1])
+
+        # erase key from slot 0
+        self.eraseKeyQmp("testdev", old_secret = self.secrets[0])
+
+        # this will fail as the old password is no longer valid
+        self.addKeyQmp("testdev", new_secret = self.secrets[2])
+
+        # this will work
+        self.addKeyQmp("testdev", new_secret = self.secrets[2], secret = self.secrets[1])
+
+        # close and erase the image for good
+        self.closeImageQmp("testdev")
+        os.remove(test_img)
+
+    def testUseForceLuke(self):
+
+        self.createImg(test_img, self.secrets[0]);
+        self.openImageQmp("testdev", test_img, self.secrets[0])
+
+        # Add bunch of secrets
+        self.addKeyQmp("testdev", new_secret = self.secrets[1], slot=4)
+        self.addKeyQmp("testdev", new_secret = self.secrets[4], slot=2)
+
+        # overwrite an active secret
+        self.addKeyQmp("testdev", new_secret = self.secrets[5], slot=2)
+        self.addKeyQmp("testdev", new_secret = self.secrets[5], slot=2, force=True)
+
+        self.addKeyQmp("testdev", new_secret = self.secrets[0])
+
+        # Now erase all the secrets
+        self.eraseKeyQmp("testdev", old_secret = self.secrets[5])
+        self.eraseKeyQmp("testdev", slot=4)
+
+        # erase last keyslot
+        self.eraseKeyQmp("testdev", old_secret = self.secrets[0])
+        self.eraseKeyQmp("testdev", old_secret = self.secrets[0], force=True)
+
+        self.closeImageQmp("testdev")
+        os.remove(test_img)
+
+
+if __name__ == '__main__':
+    iotests.verify_working_luks()
+    # Encrypted formats support
+    iotests.activate_logging()
+    iotests.main(supported_fmts = ['qcow2', 'luks'])
diff --git a/tests/qemu-iotests/295.out b/tests/qemu-iotests/295.out
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/295.out
@@ -XXX,XX +XXX,XX @@
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_erase_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_erase_key"}}
+{"return": {}}
+Job failed: Invalid password, cannot unlock any keyslot
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+Job failed: Refusing to overwrite active keyslot 2 - please erase it first
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_add_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_erase_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_erase_key"}}
+{"return": {}}
+Job failed: All the active keyslots match the (old) password that was given and erasing them will erase all the data in the image irreversibly - refusing operation
+{"execute": "job-dismiss", "arguments": {"id": "job_erase_key"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job_erase_key"}}
+{"return": {}}
+...
+----------------------------------------------------------------------
+Ran 3 tests
+
+OK
diff --git a/tests/qemu-iotests/296 b/tests/qemu-iotests/296
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/296
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Test case for encryption key management versus image sharing
+#
+# Copyright (C) 2019 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+import iotests
+import os
+import time
+import json
+
+test_img = os.path.join(iotests.test_dir, 'test.img')
+
+class Secret:
+    def __init__(self, index):
+        self._id = "keysec" + str(index)
+        # you are not supposed to see the password...
+        self._secret = "hunter" + str(index)
+
+    def id(self):
+        return self._id
+
+    def secret(self):
+        return self._secret
+
+    def to_cmdline_object(self):
+        return  [ "secret,id=" + self._id + ",data=" + self._secret]
+
+    def to_qmp_object(self):
+        return { "qom_type" : "secret", "id": self.id(),
+                 "props": { "data": self.secret() } }
+
+################################################################################
+
+class EncryptionSetupTestCase(iotests.QMPTestCase):
+
+    # test case startup
+    def setUp(self):
+
+        # start the VMs
+        self.vm1 = iotests.VM(path_suffix = 'VM1')
+        self.vm2 = iotests.VM(path_suffix = 'VM2')
+        self.vm1.launch()
+        self.vm2.launch()
+
+        # create the secrets and load 'em into the VMs
+        self.secrets = [ Secret(i) for i in range(0, 4) ]
+        for secret in self.secrets:
+            result = self.vm1.qmp("object-add", **secret.to_qmp_object())
+            self.assert_qmp(result, 'return', {})
+            result = self.vm2.qmp("object-add", **secret.to_qmp_object())
+            self.assert_qmp(result, 'return', {})
+
+    # test case shutdown
+    def tearDown(self):
+        # stop the VM
+        self.vm1.shutdown()
+        self.vm2.shutdown()
+
+    ###########################################################################
+    # create the encrypted block device using qemu-img
+    def createImg(self, file, secret):
+
+        output = iotests.qemu_img_pipe(
+            'create',
+            '--object', *secret.to_cmdline_object(),
+            '-f', iotests.imgfmt,
+            '-o', 'key-secret=' + secret.id(),
+            '-o', 'iter-time=10',
+            file,
+            '1M')
+
+        iotests.log(output, filters=[iotests.filter_test_dir])
+
+    # attempts to add a key using qemu-img
+    def addKey(self, file, secret, new_secret):
+
+        image_options = {
+            'key-secret' : secret.id(),
+            'driver' : iotests.imgfmt,
+            'file' : {
+                'driver':'file',
+                'filename': file,
+                }
+            }
+
+        output = iotests.qemu_img_pipe(
+            'amend',
+            '--object', *secret.to_cmdline_object(),
+            '--object', *new_secret.to_cmdline_object(),
+
+            '-o', 'state=active',
+            '-o', 'new-secret=' + new_secret.id(),
+            '-o', 'iter-time=10',
+
+            "json:" + json.dumps(image_options)
+            )
+
+        iotests.log(output, filters=[iotests.filter_test_dir])
+
+    ###########################################################################
+    # open an encrypted block device
+    def openImageQmp(self, vm, id, file, secret,
+                     readOnly = False, reOpen = False):
+
+        command = 'x-blockdev-reopen' if reOpen else 'blockdev-add'
+
+        result = vm.qmp(command, **
+            {
+                'driver': iotests.imgfmt,
+                'node-name': id,
+                'read-only': readOnly,
+                'key-secret' : secret.id(),
+                'file': {
+                    'driver': 'file',
+                    'filename': test_img,
+                }
+            }
+        )
+        self.assert_qmp(result, 'return', {})
+
+    # close the encrypted block device
+    def closeImageQmp(self, vm, id):
+        result = vm.qmp('blockdev-del', **{ 'node-name': id })
+        self.assert_qmp(result, 'return', {})
+
+    ###########################################################################
+
+    # add a key to an encrypted block device
+    def addKeyQmp(self, vm, id, new_secret):
+
+        args = {
+            'node-name': id,
+            'job-id' : 'job0',
+            'options' : {
+                'state'     : 'active',
+                'driver'    : iotests.imgfmt,
+                'new-secret': new_secret.id(),
+                'iter-time' : 10
+            },
+        }
+
+        result = vm.qmp('x-blockdev-amend', **args)
+        assert result['return'] == {}
+        vm.run_job('job0')
+
+    # test that when the image opened by two qemu processes,
+    # neither of them can update the image
+    def test1(self):
+        self.createImg(test_img, self.secrets[0]);
+
+        # VM1 opens the image and adds a key
+        self.openImageQmp(self.vm1, "testdev", test_img, self.secrets[0])
+        self.addKeyQmp(self.vm1, "testdev", new_secret = self.secrets[1])
+
+
+        # VM2 opens the image
+        self.openImageQmp(self.vm2, "testdev", test_img, self.secrets[0])
+
+
+        # neither VMs now should be able to add a key
+        self.addKeyQmp(self.vm1, "testdev", new_secret = self.secrets[2])
+        self.addKeyQmp(self.vm2, "testdev", new_secret = self.secrets[2])
+
+
+        # VM 1 closes the image
+        self.closeImageQmp(self.vm1, "testdev")
+
+
+        # now VM2 can add the key
+        self.addKeyQmp(self.vm2, "testdev", new_secret = self.secrets[2])
+
+
+        # qemu-img should also not be able to add a key
+        self.addKey(test_img, self.secrets[0], self.secrets[2])
+
+        # cleanup
+        self.closeImageQmp(self.vm2, "testdev")
+        os.remove(test_img)
+
+
+    def test2(self):
+        self.createImg(test_img, self.secrets[0]);
+
+        # VM1 opens the image readonly
+        self.openImageQmp(self.vm1, "testdev", test_img, self.secrets[0],
+                          readOnly = True)
+
+        # VM2 opens the image
+        self.openImageQmp(self.vm2, "testdev", test_img, self.secrets[0])
+
+        # VM1 can't add a key since image is readonly
+        self.addKeyQmp(self.vm1, "testdev", new_secret = self.secrets[2])
+
+        # VM2 can't add a key since VM is has the image opened
+        self.addKeyQmp(self.vm2, "testdev", new_secret = self.secrets[2])
+
+
+        #VM1 reopens the image read-write
+        self.openImageQmp(self.vm1, "testdev", test_img, self.secrets[0],
+                          reOpen = True, readOnly = False)
+
+        # VM1 still can't add the key
+        self.addKeyQmp(self.vm1, "testdev", new_secret = self.secrets[2])
+
+        # VM2 gets away
+        self.closeImageQmp(self.vm2, "testdev")
+
+        # VM1 now can add the key
+        self.addKeyQmp(self.vm1, "testdev", new_secret = self.secrets[2])
+
+        self.closeImageQmp(self.vm1, "testdev")
+        os.remove(test_img)
+
+
+if __name__ == '__main__':
+    # support only raw luks since luks encrypted qcow2 is a proper
+    # format driver which doesn't allow any sharing
+    iotests.activate_logging()
+    iotests.main(supported_fmts = ['luks'])
diff --git a/tests/qemu-iotests/296.out b/tests/qemu-iotests/296.out
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/296.out
@@ -XXX,XX +XXX,XX @@
+Formatting 'TEST_DIR/test.img', fmt=luks size=1048576 key-secret=keysec0 iter-time=10
+
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+Job failed: Failed to get shared "consistent read" lock
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+Job failed: Failed to get shared "consistent read" lock
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+qemu-img: Failed to get shared "consistent read" lock
+Is another process using the image [TEST_DIR/test.img]?
+
+Formatting 'TEST_DIR/test.img', fmt=luks size=1048576 key-secret=keysec0 iter-time=10
+
+Job failed: Block node is read-only
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+Job failed: Failed to get shared "consistent read" lock
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+Job failed: Failed to get shared "consistent read" lock
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+{"execute": "job-dismiss", "arguments": {"id": "job0"}}
+{"return": {}}
+..
+----------------------------------------------------------------------
+Ran 2 tests
+
+OK
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -XXX,XX +XXX,XX @@
 292 rw auto quick
 293 rw
 294 rw quick
+295 rw
+296 rw
 297 meta
-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

qemu-img convert wants to distinguish ZERO which comes from short
backing files. unallocated_blocks_are_zero field of bdi is unrelated:
space after EOF is always considered to be zero anyway. So, just make
post_backing_zero true in case of short backing file.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200528094405.145708-2-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qemu-img.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/qemu-img.c b/qemu-img.c
index XXXXXXX..XXXXXXX 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -XXX,XX +XXX,XX @@ typedef struct ImgConvertState {
     BlockBackend *target;
     bool has_zero_init;
     bool compressed;
-    bool unallocated_blocks_are_zero;
     bool target_is_new;
     bool target_has_backing;
     int64_t target_backing_sectors; /* negative if unknown */
@@ -XXX,XX +XXX,XX @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
 
     if (s->target_backing_sectors >= 0) {
         if (sector_num >= s->target_backing_sectors) {
-            post_backing_zero = s->unallocated_blocks_are_zero;
+            post_backing_zero = true;
         } else if (sector_num + n > s->target_backing_sectors) {
             /* Split requests around target_backing_sectors (because
              * starting from there, zeros are handled differently) */
@@ -XXX,XX +XXX,XX @@ static int img_convert(int argc, char **argv)
     } else {
         s.compressed = s.compressed || bdi.needs_compressed_writes;
         s.cluster_sectors = bdi.cluster_size / BDRV_SECTOR_SIZE;
-        s.unallocated_blocks_are_zero = bdi.unallocated_blocks_are_zero;
     }
 
     ret = convert_do_copy(&s);
-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

The function has only one user: bdrv_co_block_status(). Inline it to
simplify reviewing of the following patches, which will finally drop
unallocated_blocks_are_zero field too.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200528094405.145708-3-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block.h |  1 -
 block.c               | 15 ---------------
 block/io.c            | 11 ++++++++---
 3 files changed, 8 insertions(+), 19 deletions(-)

diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ int bdrv_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes);
 int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes);
 int bdrv_has_zero_init_1(BlockDriverState *bs);
 int bdrv_has_zero_init(BlockDriverState *bs);
-bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs);
 bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
 int bdrv_block_status(BlockDriverState *bs, int64_t offset,
                       int64_t bytes, int64_t *pnum, int64_t *map,
diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ int bdrv_has_zero_init(BlockDriverState *bs)
     return 0;
 }
 
-bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs)
-{
-    BlockDriverInfo bdi;
-
-    if (bs->backing) {
-        return false;
-    }
-
-    if (bdrv_get_info(bs, &bdi) == 0) {
-        return bdi.unallocated_blocks_are_zero;
-    }
-
-    return false;
-}
-
 bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs)
 {
     if (!(bs->open_flags & BDRV_O_UNMAP)) {
diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
     if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
         ret |= BDRV_BLOCK_ALLOCATED;
     } else if (want_zero) {
-        if (bdrv_unallocated_blocks_are_zero(bs)) {
-            ret |= BDRV_BLOCK_ZERO;
-        } else if (bs->backing) {
+        if (bs->backing) {
             BlockDriverState *bs2 = bs->backing->bs;
             int64_t size2 = bdrv_getlength(bs2);
 
             if (size2 >= 0 && offset >= size2) {
                 ret |= BDRV_BLOCK_ZERO;
             }
+        } else {
+            BlockDriverInfo bdi;
+            int ret2 = bdrv_get_info(bs, &bdi);
+
+            if (ret2 == 0 && bdi.unallocated_blocks_are_zero) {
+                ret |= BDRV_BLOCK_ZERO;
+            }
         }
     }
 
-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

In case of !VDI_IS_ALLOCATED[], we do zero out the corresponding chunk
of qiov. So, this should be reported as ZERO.

Note that this changes visible output of "qemu-img map --output=json"
and "qemu-io -c map" commands. For qemu-img map, the change is obvious:
we just mark as zero what is really zero. For qemu-io it's less
obvious: what was unallocated now is allocated.

There is an inconsistency in understanding of unallocated regions in
Qemu: backing-supporting format-drivers return 0 block-status to report
go-to-backing logic for this area. Some protocol-drivers (iscsi) return
0 to report fs-unallocated-non-zero status (i.e., don't occupy space on
disk, read result is undefined).

BDRV_BLOCK_ALLOCATED is defined as something more close to
go-to-backing logic. Still it is calculated as ZERO | DATA, so 0 from
iscsi is treated as unallocated. It doesn't influence backing-chain
behavior, as iscsi can't have backing file. But it does influence
"qemu-io -c map".

We should solve this inconsistency at some future point. Now, let's
just make backing-not-supporting format drivers (vdi at this patch and
vpc with the following) to behave more like backing-supporting drivers
and not report 0 block-status. More over, returning ZERO status is
absolutely valid thing, and again, corresponds to how the other
format-drivers (backing-supporting) work.

After block-status update, it never reports 0, so setting
unallocated_blocks_are_zero doesn't make sense (as the only user of it
is bdrv_co_block_status and it checks unallocated_blocks_are_zero only
for unallocated areas). Drop it.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200528094405.145708-4-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/vdi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/block/vdi.c b/block/vdi.c
index XXXXXXX..XXXXXXX 100644
--- a/block/vdi.c
+++ b/block/vdi.c
@@ -XXX,XX +XXX,XX @@ static int vdi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     logout("\n");
     bdi->cluster_size = s->block_size;
     bdi->vm_state_offset = 0;
-    bdi->unallocated_blocks_are_zero = true;
     return 0;
 }
 
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_block_status(BlockDriverState *bs,
     *pnum = MIN(s->block_size - index_in_block, bytes);
     result = VDI_IS_ALLOCATED(bmap_entry);
     if (!result) {
-        return 0;
+        return BDRV_BLOCK_ZERO;
     }
 
     *map = s->header.offset_data + (uint64_t)bmap_entry * s->block_size +
-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

In case when get_image_offset() returns -1, we do zero out the
corresponding chunk of qiov. So, this should be reported as ZERO.

We should solve this inconsistency at some future point. Now, let's
just make backing-not-supporting format drivers (vdi in the previous
patch and vpc now) to behave more like backing-supporting drivers
and not report 0 block-status. More over, returning ZERO status is
absolutely valid thing, and again, corresponds to how the other
format-drivers (backing-supporting) work.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200528094405.145708-5-vsementsov@virtuozzo.com>
[mreitz: qemu-io -c map as used by iotest 146 now reports everything as
         allocated; in order to make the test do something useful, we
         use qemu-img map --output=json now]
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/vpc.c                |   3 +-
 tests/qemu-iotests/146     |  60 ++++--
 tests/qemu-iotests/146.out | 405 +++++++++++++++++++++++++++++++++++--
 3 files changed, 436 insertions(+), 32 deletions(-)

diff --git a/block/vpc.c b/block/vpc.c
index XXXXXXX..XXXXXXX 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -XXX,XX +XXX,XX @@ static int vpc_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
         bdi->cluster_size = s->block_size;
     }
 
-    bdi->unallocated_blocks_are_zero = true;
     return 0;
 }
 
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_block_status(BlockDriverState *bs,
     image_offset = get_image_offset(bs, offset, false, NULL);
     allocated = (image_offset != -1);
     *pnum = 0;
-    ret = 0;
+    ret = BDRV_BLOCK_ZERO;
 
     do {
         /* All sectors in a block are contiguous (without using the bitmap) */
diff --git a/tests/qemu-iotests/146 b/tests/qemu-iotests/146
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/146
+++ b/tests/qemu-iotests/146
@@ -XXX,XX +XXX,XX @@ echo === Testing VPC Autodetect ===
 echo
 _use_sample_img virtualpc-dynamic.vhd.bz2
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing VPC with current_size force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing VPC with chs force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 _cleanup_test_img
 
@@ -XXX,XX +XXX,XX @@ echo === Testing Hyper-V Autodetect ===
 echo
 _use_sample_img hyperv2012r2-dynamic.vhd.bz2
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing Hyper-V with current_size force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing Hyper-V with chs force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 _cleanup_test_img
 
@@ -XXX,XX +XXX,XX @@ echo === Testing d2v Autodetect ===
 echo
 _use_sample_img d2v-zerofilled.vhd.bz2
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing d2v with current_size force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing d2v with chs force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 _cleanup_test_img
 
@@ -XXX,XX +XXX,XX @@ echo
 echo === Read created image, default opts ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=chs ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=current_size ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing Image create, force_size ===
@@ -XXX,XX +XXX,XX @@ echo
 echo === Read created image, default opts ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=chs ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=current_size ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo "*** done"
 rm -f $seq.full
diff --git a/tests/qemu-iotests/146.out b/tests/qemu-iotests/146.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/146.out
+++ b/tests/qemu-iotests/146.out
@@ -XXX,XX +XXX,XX @@ QA output created by 146
 
 === Testing VPC Autodetect ===
 
-126.998 GiB (0x1fbfe04000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 136363130880, "depth": 0, "zero": true, "data": false }]
 
 === Testing VPC with current_size force ===
 
-127 GiB (0x1fc0000000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 136365211648, "depth": 0, "zero": true, "data": false }]
 
 === Testing VPC with chs force ===
 
-126.998 GiB (0x1fbfe04000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 136363130880, "depth": 0, "zero": true, "data": false }]
 
 === Testing Hyper-V Autodetect ===
 
-127 GiB (0x1fc0000000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 136365211648, "depth": 0, "zero": true, "data": false }]
 
 === Testing Hyper-V with current_size force ===
 
-127 GiB (0x1fc0000000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 136365211648, "depth": 0, "zero": true, "data": false }]
 
 === Testing Hyper-V with chs force ===
 
-126.998 GiB (0x1fbfe04000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 136363130880, "depth": 0, "zero": true, "data": false }]
 
 === Testing d2v Autodetect ===
 
-251.250 MiB (0xfb40000) bytes     allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 2097152, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 4194304, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 6291456, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 8388608, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 10485760, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 12582912, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 14680064, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 16777216, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 18874368, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 20971520, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 23068672, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 25165824, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 27262976, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 29360128, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 31457280, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 33554432, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 35651584, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 37748736, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 39845888, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 41943040, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 44040192, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 46137344, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 48234496, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 50331648, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 52428800, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 54525952, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 56623104, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 58720256, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 60817408, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 62914560, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 65011712, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 67108864, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 69206016, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 71303168, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 73400320, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 75497472, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 77594624, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 79691776, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 81788928, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 83886080, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 85983232, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 88080384, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 90177536, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 92274688, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 94371840, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 96468992, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 98566144, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 100663296, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 102760448, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 104857600, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 106954752, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 109051904, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 111149056, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 113246208, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 115343360, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 117440512, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 119537664, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 121634816, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 123731968, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 125829120, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 127926272, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 130023424, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 132120576, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 134217728, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 136314880, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 138412032, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 140509184, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 142606336, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 144703488, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 146800640, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 148897792, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 150994944, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 153092096, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 155189248, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 157286400, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 159383552, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 161480704, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 163577856, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 165675008, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 167772160, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 169869312, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 171966464, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 174063616, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 176160768, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 178257920, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 180355072, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 182452224, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 184549376, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 186646528, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 188743680, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 190840832, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 192937984, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 195035136, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 197132288, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 199229440, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 201326592, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 203423744, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 205520896, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 207618048, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 209715200, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 211812352, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 213909504, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 216006656, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 218103808, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 220200960, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 222298112, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 224395264, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 226492416, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 228589568, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 230686720, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 232783872, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 234881024, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 236978176, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 239075328, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 241172480, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 243269632, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 245366784, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 247463936, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 249561088, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 251658240, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 253755392, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 255852544, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 257949696, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 260046848, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 262144000, "length": 1310720, "depth": 0, "zero": false, "data": true, "offset": OFFSET }]
 
 === Testing d2v with current_size force ===
 
-251.250 MiB (0xfb40000) bytes     allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 2097152, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 4194304, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 6291456, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 8388608, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 10485760, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 12582912, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 14680064, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 16777216, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 18874368, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 20971520, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 23068672, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 25165824, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 27262976, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 29360128, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 31457280, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 33554432, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 35651584, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 37748736, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 39845888, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 41943040, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 44040192, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 46137344, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 48234496, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 50331648, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 52428800, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 54525952, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 56623104, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 58720256, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 60817408, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 62914560, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 65011712, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 67108864, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 69206016, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 71303168, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 73400320, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 75497472, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 77594624, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 79691776, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 81788928, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 83886080, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 85983232, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 88080384, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 90177536, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 92274688, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 94371840, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 96468992, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 98566144, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 100663296, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 102760448, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 104857600, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 106954752, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 109051904, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 111149056, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 113246208, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 115343360, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 117440512, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 119537664, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 121634816, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 123731968, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 125829120, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 127926272, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 130023424, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 132120576, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 134217728, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 136314880, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 138412032, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 140509184, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 142606336, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 144703488, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 146800640, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 148897792, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 150994944, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 153092096, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 155189248, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 157286400, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 159383552, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 161480704, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 163577856, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 165675008, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 167772160, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 169869312, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 171966464, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 174063616, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 176160768, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 178257920, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 180355072, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 182452224, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 184549376, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 186646528, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 188743680, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 190840832, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 192937984, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 195035136, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 197132288, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 199229440, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 201326592, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 203423744, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 205520896, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 207618048, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 209715200, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 211812352, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 213909504, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 216006656, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 218103808, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 220200960, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 222298112, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 224395264, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 226492416, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 228589568, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 230686720, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 232783872, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 234881024, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 236978176, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 239075328, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 241172480, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 243269632, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 245366784, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 247463936, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 249561088, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 251658240, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 253755392, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 255852544, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 257949696, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 260046848, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 262144000, "length": 1310720, "depth": 0, "zero": false, "data": true, "offset": OFFSET }]
 
 === Testing d2v with chs force ===
 
-251.250 MiB (0xfb40000) bytes     allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 2097152, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 4194304, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 6291456, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 8388608, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 10485760, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 12582912, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 14680064, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 16777216, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 18874368, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 20971520, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 23068672, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 25165824, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 27262976, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 29360128, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 31457280, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 33554432, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 35651584, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 37748736, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 39845888, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 41943040, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 44040192, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 46137344, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 48234496, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 50331648, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 52428800, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 54525952, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 56623104, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 58720256, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 60817408, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 62914560, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 65011712, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 67108864, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 69206016, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 71303168, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 73400320, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 75497472, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 77594624, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 79691776, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 81788928, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 83886080, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 85983232, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 88080384, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 90177536, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 92274688, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 94371840, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 96468992, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 98566144, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 100663296, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 102760448, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 104857600, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 106954752, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 109051904, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 111149056, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 113246208, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 115343360, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 117440512, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 119537664, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 121634816, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 123731968, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 125829120, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 127926272, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 130023424, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 132120576, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 134217728, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 136314880, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 138412032, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 140509184, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 142606336, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 144703488, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 146800640, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 148897792, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 150994944, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 153092096, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 155189248, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 157286400, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 159383552, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 161480704, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 163577856, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 165675008, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 167772160, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 169869312, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 171966464, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 174063616, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 176160768, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 178257920, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 180355072, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 182452224, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 184549376, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 186646528, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 188743680, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 190840832, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 192937984, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 195035136, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 197132288, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 199229440, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 201326592, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 203423744, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 205520896, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 207618048, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 209715200, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 211812352, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 213909504, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 216006656, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 218103808, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 220200960, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 222298112, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 224395264, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 226492416, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 228589568, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 230686720, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 232783872, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 234881024, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 236978176, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 239075328, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 241172480, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 243269632, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 245366784, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 247463936, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 249561088, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 251658240, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 253755392, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 255852544, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 257949696, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 260046848, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": OFFSET },
+{ "start": 262144000, "length": 1310720, "depth": 0, "zero": false, "data": true, "offset": OFFSET }]
 
 === Testing Image create, default ===
 
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/IMGFMT-create-test.IMGFMT', fmt=IMGFMT size=4294967296
 
 === Read created image, default opts ====
 
-4 GiB (0x10007a000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 4295467008, "depth": 0, "zero": true, "data": false }]
 
 === Read created image, force_size_calc=chs ====
 
-4 GiB (0x10007a000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 4295467008, "depth": 0, "zero": true, "data": false }]
 
 === Read created image, force_size_calc=current_size ====
 
-4 GiB (0x10007a000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 4295467008, "depth": 0, "zero": true, "data": false }]
 
 === Testing Image create, force_size ===
 
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/IMGFMT-create-test.IMGFMT', fmt=IMGFMT size=4294967296
 
 === Read created image, default opts ====
 
-4 GiB (0x100000000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 4294967296, "depth": 0, "zero": true, "data": false }]
 
 === Read created image, force_size_calc=chs ====
 
-4 GiB (0x100000000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 4294967296, "depth": 0, "zero": true, "data": false }]
 
 === Read created image, force_size_calc=current_size ====
 
-4 GiB (0x100000000) bytes not allocated at offset 0 bytes (0x0)
+[{ "start": 0, "length": 4294967296, "depth": 0, "zero": true, "data": false }]
 *** done
-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

We set bdi->unallocated_blocks_are_zero = iscsilun->lbprz, but
iscsi_co_block_status doesn't return 0 in case of iscsilun->lbprz, it
returns ZERO when appropriate. So actually unallocated_blocks_are_zero
is useless (it doesn't affect the only user of the field:
bdrv_co_block_status()). Drop it now.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200528094405.145708-7-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/iscsi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/block/iscsi.c b/block/iscsi.c
index XXXXXXX..XXXXXXX 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset,
 static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     IscsiLun *iscsilun = bs->opaque;
-    bdi->unallocated_blocks_are_zero = iscsilun->lbprz;
     bdi->cluster_size = iscsilun->cluster_size;
     return 0;
 }
-- 
2.26.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Currently this field only set by qed and qcow2. But in fact, all
backing-supporting formats (parallels, qcow, qcow2, qed, vmdk) share
these semantics: on unallocated blocks, if there is no backing file they
just memset the buffer with zeroes.

So, document this behavior for .supports_backing and drop
.unallocated_blocks_are_zero

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200528094405.145708-10-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block.h     |  5 -----
 include/block/block_int.h | 12 +++++++++++-
 block/io.c                |  9 ++-------
 block/qcow2.c             |  1 -
 block/qed.c               |  1 -
 5 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ typedef struct BlockDriverInfo {
     /* offset at which the VM state can be saved (0 if not possible) */
     int64_t vm_state_offset;
     bool is_dirty;
-    /*
-     * True if unallocated blocks read back as zeroes. This is equivalent
-     * to the LBPRZ flag in the SCSI logical block provisioning page.
-     */
-    bool unallocated_blocks_are_zero;
     /*
      * True if this block driver only supports compressed writes
      */
diff --git a/include/block/block_int.h b/include/block/block_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -XXX,XX +XXX,XX @@ struct BlockDriver {
      */
     bool bdrv_needs_filename;
 
-    /* Set if a driver can support backing files */
+    /*
+     * Set if a driver can support backing files. This also implies the
+     * following semantics:
+     *
+     *  - Return status 0 of .bdrv_co_block_status means that corresponding
+     *    blocks are not allocated in this layer of backing-chain
+     *  - For such (unallocated) blocks, read will:
+     *    - fill buffer with zeros if there is no backing file
+     *    - read from the backing file otherwise, where the block layer
+     *      takes care of reading zeros beyond EOF if backing file is short
+     */
     bool supports_backing;
 
     /* For handling image reopen for split or non-split files */
diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
 
     if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
         ret |= BDRV_BLOCK_ALLOCATED;
-    } else if (want_zero) {
+    } else if (want_zero && bs->drv->supports_backing) {
         if (bs->backing) {
             BlockDriverState *bs2 = bs->backing->bs;
             int64_t size2 = bdrv_getlength(bs2);
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
                 ret |= BDRV_BLOCK_ZERO;
             }
         } else {
-            BlockDriverInfo bdi;
-            int ret2 = bdrv_get_info(bs, &bdi);
-
-            if (ret2 == 0 && bdi.unallocated_blocks_are_zero) {
-                ret |= BDRV_BLOCK_ZERO;
-            }
+            ret |= BDRV_BLOCK_ZERO;
         }
     }
 
diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ err:
 static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     BDRVQcow2State *s = bs->opaque;
-    bdi->unallocated_blocks_are_zero = true;
     bdi->cluster_size = s->cluster_size;
     bdi->vm_state_offset = qcow2_vm_state_offset(s);
     return 0;
diff --git a/block/qed.c b/block/qed.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -XXX,XX +XXX,XX @@ static int bdrv_qed_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     memset(bdi, 0, sizeof(*bdi));
     bdi->cluster_size = s->header.cluster_size;
     bdi->is_dirty = s->header.features & QED_F_NEED_CHECK;
-    bdi->unallocated_blocks_are_zero = true;
     return 0;
 }
 
-- 
2.26.2

From: Eric Blake <eblake@redhat.com>

The other four drivers that support backing files (qcow, qcow2,
parallels, vmdk) all rely on the block layer to populate zeroes when
reading beyond EOF of a short backing file.  We can simplify the qed
code by doing likewise.

Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20200528094405.145708-11-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/qed.h |  1 -
 block/qed.c | 64 +++++------------------------------------------------
 2 files changed, 6 insertions(+), 59 deletions(-)

diff --git a/block/qed.h b/block/qed.h
index XXXXXXX..XXXXXXX 100644
--- a/block/qed.h
+++ b/block/qed.h
@@ -XXX,XX +XXX,XX @@ typedef struct QEDAIOCB {
 
     /* Current cluster scatter-gather list */
     QEMUIOVector cur_qiov;
-    QEMUIOVector *backing_qiov;
     uint64_t cur_pos;               /* position on block device, in bytes */
     uint64_t cur_cluster;           /* cluster offset in image file */
     unsigned int cur_nclusters;     /* number of clusters being accessed */
diff --git a/block/qed.c b/block/qed.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -XXX,XX +XXX,XX @@ static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
  * @s:              QED state
  * @pos:            Byte position in device
  * @qiov:           Destination I/O vector
- * @backing_qiov:   Possibly shortened copy of qiov, to be allocated here
- * @cb:             Completion function
- * @opaque:         User data for completion function
  *
  * This function reads qiov->size bytes starting at pos from the backing file.
  * If there is no backing file then zeroes are read.
  */
 static int coroutine_fn qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
-                                              QEMUIOVector *qiov,
-                                              QEMUIOVector **backing_qiov)
+                                              QEMUIOVector *qiov)
 {
-    uint64_t backing_length = 0;
-    size_t size;
-    int ret;
-
-    /* If there is a backing file, get its length.  Treat the absence of a
-     * backing file like a zero length backing file.
-     */
     if (s->bs->backing) {
-        int64_t l = bdrv_getlength(s->bs->backing->bs);
-        if (l < 0) {
-            return l;
-        }
-        backing_length = l;
-    }
-
-    /* Zero all sectors if reading beyond the end of the backing file */
-    if (pos >= backing_length ||
-        pos + qiov->size > backing_length) {
-        qemu_iovec_memset(qiov, 0, 0, qiov->size);
-    }
-
-    /* Complete now if there are no backing file sectors to read */
-    if (pos >= backing_length) {
-        return 0;
-    }
-
-    /* If the read straddles the end of the backing file, shorten it */
-    size = MIN((uint64_t)backing_length - pos, qiov->size);
-
-    assert(*backing_qiov == NULL);
-    *backing_qiov = g_new(QEMUIOVector, 1);
-    qemu_iovec_init(*backing_qiov, qiov->niov);
-    qemu_iovec_concat(*backing_qiov, qiov, 0, size);
-
-    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
-    ret = bdrv_co_preadv(s->bs->backing, pos, size, *backing_qiov, 0);
-    if (ret < 0) {
-        return ret;
+        BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
+        return bdrv_co_preadv(s->bs->backing, pos, qiov->size, qiov, 0);
     }
+    qemu_iovec_memset(qiov, 0, 0, qiov->size);
     return 0;
 }
 
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s,
                                                    uint64_t offset)
 {
     QEMUIOVector qiov;
-    QEMUIOVector *backing_qiov = NULL;
     int ret;
 
     /* Skip copy entirely if there is no work to do */
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s,
 
     qemu_iovec_init_buf(&qiov, qemu_blockalign(s->bs, len), len);
 
-    ret = qed_read_backing_file(s, pos, &qiov, &backing_qiov);
-
-    if (backing_qiov) {
-        qemu_iovec_destroy(backing_qiov);
-        g_free(backing_qiov);
-        backing_qiov = NULL;
-    }
+    ret = qed_read_backing_file(s, pos, &qiov);
 
     if (ret) {
         goto out;
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_aio_read_data(void *opaque, int ret,
         qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size);
         r = 0;
     } else if (ret != QED_CLUSTER_FOUND) {
-        r = qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov,
-                                  &acb->backing_qiov);
+        r = qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov);
     } else {
         BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
         r = bdrv_co_preadv(bs->file, offset, acb->cur_qiov.size,
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_aio_next_io(QEDAIOCB *acb)
     while (1) {
         trace_qed_aio_next_io(s, acb, 0, acb->cur_pos + acb->cur_qiov.size);
 
-        if (acb->backing_qiov) {
-            qemu_iovec_destroy(acb->backing_qiov);
-            g_free(acb->backing_qiov);
-            acb->backing_qiov = NULL;
-        }
-
         acb->qiov_offset += acb->cur_qiov.size;
         acb->cur_pos += acb->cur_qiov.size;
         qemu_iovec_reset(&acb->cur_qiov);
-- 
2.26.2

The following changes since commit 1214d55d1c41fbab3a9973a05085b8760647e411:

Merge remote-tracking branch 'remotes/nvme/tags/nvme-next-pull-request' into staging (2021-02-09 13:24:37 +0000)

are available in the Git repository at:

https://gitlab.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to eb847c42296497978942f738cd41dc29a35a49b2:

docs: fix Parallels Image "dirty bitmap" section (2021-02-10 09:23:28 +0000)

----------------------------------------------------------------
Pull request

v4:
 * Add PCI_EXPRESS Kconfig dependency to fix s390x in "multi-process: setup PCI
   host bridge for remote device" [Philippe and Thomas]

----------------------------------------------------------------

Denis V. Lunev (1):
  docs: fix Parallels Image "dirty bitmap" section

Elena Ufimtseva (8):
  multi-process: add configure and usage information
  io: add qio_channel_writev_full_all helper
  io: add qio_channel_readv_full_all_eof & qio_channel_readv_full_all
    helpers
  multi-process: define MPQemuMsg format and transmission functions
  multi-process: introduce proxy object
  multi-process: add proxy communication functions
  multi-process: Forward PCI config space acceses to the remote process
  multi-process: perform device reset in the remote process

Jagannathan Raman (11):
  memory: alloc RAM from file at offset
  multi-process: Add config option for multi-process QEMU
  multi-process: setup PCI host bridge for remote device
  multi-process: setup a machine object for remote device process
  multi-process: Initialize message handler in remote device
  multi-process: Associate fd of a PCIDevice with its object
  multi-process: setup memory manager for remote device
  multi-process: PCI BAR read/write handling for proxy & remote
    endpoints
  multi-process: Synchronize remote memory
  multi-process: create IOHUB object to handle irq
  multi-process: Retrieve PCI info from remote process

John G Johnson (1):
  multi-process: add the concept description to
    docs/devel/qemu-multiprocess

Stefan Hajnoczi (6):
  .github: point Repo Lockdown bot to GitLab repo
  gitmodules: use GitLab repos instead of qemu.org
  gitlab-ci: remove redundant GitLab repo URL command
  docs: update README to use GitLab repo URLs
  pc-bios: update mirror URLs to GitLab
  get_maintainer: update repo URL to GitLab

MAINTAINERS                               |  24 +
 README.rst                                |   4 +-
 docs/devel/index.rst                      |   1 +
 docs/devel/multi-process.rst              | 966 ++++++++++++++++++++++
 docs/system/index.rst                     |   1 +
 docs/system/multi-process.rst             |  64 ++
 docs/interop/parallels.txt                |   2 +-
 configure                                 |  10 +
 meson.build                               |   5 +-
 hw/remote/trace.h                         |   1 +
 include/exec/memory.h                     |   2 +
 include/exec/ram_addr.h                   |   4 +-
 include/hw/pci-host/remote.h              |  30 +
 include/hw/pci/pci_ids.h                  |   3 +
 include/hw/remote/iohub.h                 |  42 +
 include/hw/remote/machine.h               |  38 +
 include/hw/remote/memory.h                |  19 +
 include/hw/remote/mpqemu-link.h           |  99 +++
 include/hw/remote/proxy-memory-listener.h |  28 +
 include/hw/remote/proxy.h                 |  48 ++
 include/io/channel.h                      |  78 ++
 include/qemu/mmap-alloc.h                 |   4 +-
 include/sysemu/iothread.h                 |   6 +
 backends/hostmem-memfd.c                  |   2 +-
 hw/misc/ivshmem.c                         |   3 +-
 hw/pci-host/remote.c                      |  75 ++
 hw/remote/iohub.c                         | 119 +++
 hw/remote/machine.c                       |  80 ++
 hw/remote/memory.c                        |  65 ++
 hw/remote/message.c                       | 230 ++++++
 hw/remote/mpqemu-link.c                   | 267 ++++++
 hw/remote/proxy-memory-listener.c         | 227 +++++
 hw/remote/proxy.c                         | 379 +++++++++
 hw/remote/remote-obj.c                    | 203 +++++
 io/channel.c                              | 116 ++-
 iothread.c                                |   6 +
 softmmu/memory.c                          |   3 +-
 softmmu/physmem.c                         |  12 +-
 util/mmap-alloc.c                         |   8 +-
 util/oslib-posix.c                        |   2 +-
 .github/lockdown.yml                      |   8 +-
 .gitlab-ci.yml                            |   1 -
 .gitmodules                               |  44 +-
 Kconfig.host                              |   4 +
 hw/Kconfig                                |   1 +
 hw/meson.build                            |   1 +
 hw/pci-host/Kconfig                       |   3 +
 hw/pci-host/meson.build                   |   1 +
 hw/remote/Kconfig                         |   4 +
 hw/remote/meson.build                     |  13 +
 hw/remote/trace-events                    |   4 +
 pc-bios/README                            |   4 +-
 scripts/get_maintainer.pl                 |   2 +-
 53 files changed, 3296 insertions(+), 70 deletions(-)
 create mode 100644 docs/devel/multi-process.rst
 create mode 100644 docs/system/multi-process.rst
 create mode 100644 hw/remote/trace.h
 create mode 100644 include/hw/pci-host/remote.h
 create mode 100644 include/hw/remote/iohub.h
 create mode 100644 include/hw/remote/machine.h
 create mode 100644 include/hw/remote/memory.h
 create mode 100644 include/hw/remote/mpqemu-link.h
 create mode 100644 include/hw/remote/proxy-memory-listener.h
 create mode 100644 include/hw/remote/proxy.h
 create mode 100644 hw/pci-host/remote.c
 create mode 100644 hw/remote/iohub.c
 create mode 100644 hw/remote/machine.c
 create mode 100644 hw/remote/memory.c
 create mode 100644 hw/remote/message.c
 create mode 100644 hw/remote/mpqemu-link.c
 create mode 100644 hw/remote/proxy-memory-listener.c
 create mode 100644 hw/remote/proxy.c
 create mode 100644 hw/remote/remote-obj.c
 create mode 100644 hw/remote/Kconfig
 create mode 100644 hw/remote/meson.build
 create mode 100644 hw/remote/trace-events

-- 
2.29.2

Use the GitLab repo URL as the main repo location in order to reduce
load on qemu.org.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-id: 20210111115017.156802-2-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 .github/lockdown.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/lockdown.yml b/.github/lockdown.yml
index XXXXXXX..XXXXXXX 100644
--- a/.github/lockdown.yml
+++ b/.github/lockdown.yml
@@ -XXX,XX +XXX,XX @@ issues:
   comment: |
     Thank you for your interest in the QEMU project.
 
-    This repository is a read-only mirror of the project's master
-    repostories hosted on https://git.qemu.org/git/qemu.git.
+    This repository is a read-only mirror of the project's repostories hosted
+    at https://gitlab.com/qemu-project/qemu.git.
     The project does not process issues filed on GitHub.
 
     The project issues are tracked on Launchpad:
@@ -XXX,XX +XXX,XX @@ pulls:
   comment: |
     Thank you for your interest in the QEMU project.
 
-    This repository is a read-only mirror of the project's master
-    repostories hosted on https://git.qemu.org/git/qemu.git.
+    This repository is a read-only mirror of the project's repostories hosted
+    on https://gitlab.com/qemu-project/qemu.git.
     The project does not process merge requests filed on GitHub.
 
     QEMU welcomes contributions of code (either fixing bugs or adding new
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-3-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 .gitmodules | 44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/.gitmodules b/.gitmodules
index XXXXXXX..XXXXXXX 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -XXX,XX +XXX,XX @@
 [submodule "roms/seabios"]
 	path = roms/seabios
-	url = https://git.qemu.org/git/seabios.git/
+	url = https://gitlab.com/qemu-project/seabios.git/
 [submodule "roms/SLOF"]
 	path = roms/SLOF
-	url = https://git.qemu.org/git/SLOF.git
+	url = https://gitlab.com/qemu-project/SLOF.git
 [submodule "roms/ipxe"]
 	path = roms/ipxe
-	url = https://git.qemu.org/git/ipxe.git
+	url = https://gitlab.com/qemu-project/ipxe.git
 [submodule "roms/openbios"]
 	path = roms/openbios
-	url = https://git.qemu.org/git/openbios.git
+	url = https://gitlab.com/qemu-project/openbios.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
-	url = https://git.qemu.org/git/qemu-palcode.git
+	url = https://gitlab.com/qemu-project/qemu-palcode.git
 [submodule "roms/sgabios"]
 	path = roms/sgabios
-	url = https://git.qemu.org/git/sgabios.git
+	url = https://gitlab.com/qemu-project/sgabios.git
 [submodule "dtc"]
 	path = dtc
-	url = https://git.qemu.org/git/dtc.git
+	url = https://gitlab.com/qemu-project/dtc.git
 [submodule "roms/u-boot"]
 	path = roms/u-boot
-	url = https://git.qemu.org/git/u-boot.git
+	url = https://gitlab.com/qemu-project/u-boot.git
 [submodule "roms/skiboot"]
 	path = roms/skiboot
-	url = https://git.qemu.org/git/skiboot.git
+	url = https://gitlab.com/qemu-project/skiboot.git
 [submodule "roms/QemuMacDrivers"]
 	path = roms/QemuMacDrivers
-	url = https://git.qemu.org/git/QemuMacDrivers.git
+	url = https://gitlab.com/qemu-project/QemuMacDrivers.git
 [submodule "ui/keycodemapdb"]
 	path = ui/keycodemapdb
-	url = https://git.qemu.org/git/keycodemapdb.git
+	url = https://gitlab.com/qemu-project/keycodemapdb.git
 [submodule "capstone"]
 	path = capstone
-	url = https://git.qemu.org/git/capstone.git
+	url = https://gitlab.com/qemu-project/capstone.git
 [submodule "roms/seabios-hppa"]
 	path = roms/seabios-hppa
-	url = https://git.qemu.org/git/seabios-hppa.git
+	url = https://gitlab.com/qemu-project/seabios-hppa.git
 [submodule "roms/u-boot-sam460ex"]
 	path = roms/u-boot-sam460ex
-	url = https://git.qemu.org/git/u-boot-sam460ex.git
+	url = https://gitlab.com/qemu-project/u-boot-sam460ex.git
 [submodule "tests/fp/berkeley-testfloat-3"]
 	path = tests/fp/berkeley-testfloat-3
-	url = https://git.qemu.org/git/berkeley-testfloat-3.git
+	url = https://gitlab.com/qemu-project/berkeley-testfloat-3.git
 [submodule "tests/fp/berkeley-softfloat-3"]
 	path = tests/fp/berkeley-softfloat-3
-	url = https://git.qemu.org/git/berkeley-softfloat-3.git
+	url = https://gitlab.com/qemu-project/berkeley-softfloat-3.git
 [submodule "roms/edk2"]
 	path = roms/edk2
-	url = https://git.qemu.org/git/edk2.git
+	url = https://gitlab.com/qemu-project/edk2.git
 [submodule "slirp"]
 	path = slirp
-	url = https://git.qemu.org/git/libslirp.git
+	url = https://gitlab.com/qemu-project/libslirp.git
 [submodule "roms/opensbi"]
 	path = roms/opensbi
-	url = 	https://git.qemu.org/git/opensbi.git
+	url = 	https://gitlab.com/qemu-project/opensbi.git
 [submodule "roms/qboot"]
 	path = roms/qboot
-	url = https://git.qemu.org/git/qboot.git
+	url = https://gitlab.com/qemu-project/qboot.git
 [submodule "meson"]
 	path = meson
-	url = https://git.qemu.org/git/meson.git
+	url = https://gitlab.com/qemu-project/meson.git
 [submodule "roms/vbootrom"]
 	path = roms/vbootrom
-	url = https://git.qemu.org/git/vbootrom.git
+	url = https://gitlab.com/qemu-project/vbootrom.git
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-5-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 README.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.rst b/README.rst
index XXXXXXX..XXXXXXX 100644
--- a/README.rst
+++ b/README.rst
@@ -XXX,XX +XXX,XX @@ The QEMU source code is maintained under the GIT version control system.
 
 .. code-block:: shell
 
-   git clone https://git.qemu.org/git/qemu.git
+   git clone https://gitlab.com/qemu-project/qemu.git
 
 When submitting patches, one common approach is to use 'git
 format-patch' and/or 'git send-email' to format & send the mail to the
@@ -XXX,XX +XXX,XX @@ The QEMU website is also maintained under source control.
 
 .. code-block:: shell
 
-  git clone https://git.qemu.org/git/qemu-web.git
+  git clone https://gitlab.com/qemu-project/qemu-web.git
 
 * `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_
 
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-6-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 pc-bios/README | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pc-bios/README b/pc-bios/README
index XXXXXXX..XXXXXXX 100644
--- a/pc-bios/README
+++ b/pc-bios/README
@@ -XXX,XX +XXX,XX @@
   legacy x86 software to communicate with an attached serial console as
   if a video card were attached.  The master sources reside in a subversion
   repository at http://sgabios.googlecode.com/svn/trunk.  A git mirror is
-  available at https://git.qemu.org/git/sgabios.git.
+  available at https://gitlab.com/qemu-project/sgabios.git.
 
 - The PXE roms come from the iPXE project. Built with BANNER_TIME 0.
   Sources available at http://ipxe.org.  Vendor:Device ID -> ROM mapping:
@@ -XXX,XX +XXX,XX @@
 
 - The u-boot binary for e500 comes from the upstream denx u-boot project where
   it was compiled using the qemu-ppce500 target.
-  A git mirror is available at: https://git.qemu.org/git/u-boot.git
+  A git mirror is available at: https://gitlab.com/qemu-project/u-boot.git
   The hash used to compile the current version is: 2072e72
 
 - Skiboot (https://github.com/open-power/skiboot/) is an OPAL
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-7-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 scripts/get_maintainer.pl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index XXXXXXX..XXXXXXX 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -XXX,XX +XXX,XX @@ sub vcs_exists {
 	warn("$P: No supported VCS found.  Add --nogit to options?\n");
 	warn("Using a git repository produces better results.\n");
 	warn("Try latest git repository using:\n");
-	warn("git clone https://git.qemu.org/git/qemu.git\n");
+	warn("git clone https://gitlab.com/qemu-project/qemu.git\n");
 	$printed_novcs = 1;
     }
     return 0;
-- 
2.29.2

From: John G Johnson <john.g.johnson@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 02a68adef99f5df6a380bf8fd7b90948777e411c.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                  |   7 +
 docs/devel/index.rst         |   1 +
 docs/devel/multi-process.rst | 966 +++++++++++++++++++++++++++++++++++
 3 files changed, 974 insertions(+)
 create mode 100644 docs/devel/multi-process.rst

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ S: Maintained
 F: hw/semihosting/
 F: include/hw/semihosting/
 
+Multi-process QEMU
+M: Elena Ufimtseva <elena.ufimtseva@oracle.com>
+M: Jagannathan Raman <jag.raman@oracle.com>
+M: John G Johnson <john.g.johnson@oracle.com>
+S: Maintained
+F: docs/devel/multi-process.rst
+
 Build and test automation
 -------------------------
 Build and test automation
diff --git a/docs/devel/index.rst b/docs/devel/index.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/devel/index.rst
+++ b/docs/devel/index.rst
@@ -XXX,XX +XXX,XX @@ Contents:
    clocks
    qom
    block-coroutine-wrapper
+   multi-process
diff --git a/docs/devel/multi-process.rst b/docs/devel/multi-process.rst
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/docs/devel/multi-process.rst
@@ -XXX,XX +XXX,XX @@
+This is the design document for multi-process QEMU. It does not
+necessarily reflect the status of the current implementation, which
+may lack features or be considerably different from what is described
+in this document. This document is still useful as a description of
+the goals and general direction of this feature.
+
+Please refer to the following wiki for latest details:
+https://wiki.qemu.org/Features/MultiProcessQEMU
+
+Multi-process QEMU
+===================
+
+QEMU is often used as the hypervisor for virtual machines running in the
+Oracle cloud. Since one of the advantages of cloud computing is the
+ability to run many VMs from different tenants in the same cloud
+infrastructure, a guest that compromised its hypervisor could
+potentially use the hypervisor's access privileges to access data it is
+not authorized for.
+
+QEMU can be susceptible to security attacks because it is a large,
+monolithic program that provides many features to the VMs it services.
+Many of these features can be configured out of QEMU, but even a reduced
+configuration QEMU has a large amount of code a guest can potentially
+attack. Separating QEMU reduces the attack surface by aiding to
+limit each component in the system to only access the resources that
+it needs to perform its job.
+
+QEMU services
+-------------
+
+QEMU can be broadly described as providing three main services. One is a
+VM control point, where VMs can be created, migrated, re-configured, and
+destroyed. A second is to emulate the CPU instructions within the VM,
+often accelerated by HW virtualization features such as Intel's VT
+extensions. Finally, it provides IO services to the VM by emulating HW
+IO devices, such as disk and network devices.
+
+A multi-process QEMU
+~~~~~~~~~~~~~~~~~~~~
+
+A multi-process QEMU involves separating QEMU services into separate
+host processes. Each of these processes can be given only the privileges
+it needs to provide its service, e.g., a disk service could be given
+access only to the disk images it provides, and not be allowed to
+access other files, or any network devices. An attacker who compromised
+this service would not be able to use this exploit to access files or
+devices beyond what the disk service was given access to.
+
+A QEMU control process would remain, but in multi-process mode, will
+have no direct interfaces to the VM. During VM execution, it would still
+provide the user interface to hot-plug devices or live migrate the VM.
+
+A first step in creating a multi-process QEMU is to separate IO services
+from the main QEMU program, which would continue to provide CPU
+emulation. i.e., the control process would also be the CPU emulation
+process. In a later phase, CPU emulation could be separated from the
+control process.
+
+Separating IO services
+----------------------
+
+Separating IO services into individual host processes is a good place to
+begin for a couple of reasons. One is the sheer number of IO devices QEMU
+can emulate provides a large surface of interfaces which could potentially
+be exploited, and, indeed, have been a source of exploits in the past.
+Another is the modular nature of QEMU device emulation code provides
+interface points where the QEMU functions that perform device emulation
+can be separated from the QEMU functions that manage the emulation of
+guest CPU instructions. The devices emulated in the separate process are
+referred to as remote devices.
+
+QEMU device emulation
+~~~~~~~~~~~~~~~~~~~~~
+
+QEMU uses an object oriented SW architecture for device emulation code.
+Configured objects are all compiled into the QEMU binary, then objects
+are instantiated by name when used by the guest VM. For example, the
+code to emulate a device named "foo" is always present in QEMU, but its
+instantiation code is only run when the device is included in the target
+VM. (e.g., via the QEMU command line as *-device foo*)
+
+The object model is hierarchical, so device emulation code names its
+parent object (such as "pci-device" for a PCI device) and QEMU will
+instantiate a parent object before calling the device's instantiation
+code.
+
+Current separation models
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In order to separate the device emulation code from the CPU emulation
+code, the device object code must run in a different process. There are
+a couple of existing QEMU features that can run emulation code
+separately from the main QEMU process. These are examined below.
+
+vhost user model
+^^^^^^^^^^^^^^^^
+
+Virtio guest device drivers can be connected to vhost user applications
+in order to perform their IO operations. This model uses special virtio
+device drivers in the guest and vhost user device objects in QEMU, but
+once the QEMU vhost user code has configured the vhost user application,
+mission-mode IO is performed by the application. The vhost user
+application is a daemon process that can be contacted via a known UNIX
+domain socket.
+
+vhost socket
+''''''''''''
+
+As mentioned above, one of the tasks of the vhost device object within
+QEMU is to contact the vhost application and send it configuration
+information about this device instance. As part of the configuration
+process, the application can also be sent other file descriptors over
+the socket, which then can be used by the vhost user application in
+various ways, some of which are described below.
+
+vhost MMIO store acceleration
+'''''''''''''''''''''''''''''
+
+VMs are often run using HW virtualization features via the KVM kernel
+driver. This driver allows QEMU to accelerate the emulation of guest CPU
+instructions by running the guest in a virtual HW mode. When the guest
+executes instructions that cannot be executed by virtual HW mode,
+execution returns to the KVM driver so it can inform QEMU to emulate the
+instructions in SW.
+
+One of the events that can cause a return to QEMU is when a guest device
+driver accesses an IO location. QEMU then dispatches the memory
+operation to the corresponding QEMU device object. In the case of a
+vhost user device, the memory operation would need to be sent over a
+socket to the vhost application. This path is accelerated by the QEMU
+virtio code by setting up an eventfd file descriptor that the vhost
+application can directly receive MMIO store notifications from the KVM
+driver, instead of needing them to be sent to the QEMU process first.
+
+vhost interrupt acceleration
+''''''''''''''''''''''''''''
+
+Another optimization used by the vhost application is the ability to
+directly inject interrupts into the VM via the KVM driver, again,
+bypassing the need to send the interrupt back to the QEMU process first.
+The QEMU virtio setup code configures the KVM driver with an eventfd
+that triggers the device interrupt in the guest when the eventfd is
+written. This irqfd file descriptor is then passed to the vhost user
+application program.
+
+vhost access to guest memory
+''''''''''''''''''''''''''''
+
+The vhost application is also allowed to directly access guest memory,
+instead of needing to send the data as messages to QEMU. This is also
+done with file descriptors sent to the vhost user application by QEMU.
+These descriptors can be passed to ``mmap()`` by the vhost application
+to map the guest address space into the vhost application.
+
+IOMMUs introduce another level of complexity, since the address given to
+the guest virtio device to DMA to or from is not a guest physical
+address. This case is handled by having vhost code within QEMU register
+as a listener for IOMMU mapping changes. The vhost application maintains
+a cache of IOMMMU translations: sending translation requests back to
+QEMU on cache misses, and in turn receiving flush requests from QEMU
+when mappings are purged.
+
+applicability to device separation
+''''''''''''''''''''''''''''''''''
+
+Much of the vhost model can be re-used by separated device emulation. In
+particular, the ideas of using a socket between QEMU and the device
+emulation application, using a file descriptor to inject interrupts into
+the VM via KVM, and allowing the application to ``mmap()`` the guest
+should be re used.
+
+There are, however, some notable differences between how a vhost
+application works and the needs of separated device emulation. The most
+basic is that vhost uses custom virtio device drivers which always
+trigger IO with MMIO stores. A separated device emulation model must
+work with existing IO device models and guest device drivers. MMIO loads
+break vhost store acceleration since they are synchronous - guest
+progress cannot continue until the load has been emulated. By contrast,
+stores are asynchronous, the guest can continue after the store event
+has been sent to the vhost application.
+
+Another difference is that in the vhost user model, a single daemon can
+support multiple QEMU instances. This is contrary to the security regime
+desired, in which the emulation application should only be allowed to
+access the files or devices the VM it's running on behalf of can access.
+#### qemu-io model
+
+Qemu-io is a test harness used to test changes to the QEMU block backend
+object code. (e.g., the code that implements disk images for disk driver
+emulation) Qemu-io is not a device emulation application per se, but it
+does compile the QEMU block objects into a separate binary from the main
+QEMU one. This could be useful for disk device emulation, since its
+emulation applications will need to include the QEMU block objects.
+
+New separation model based on proxy objects
+-------------------------------------------
+
+A different model based on proxy objects in the QEMU program
+communicating with remote emulation programs could provide separation
+while minimizing the changes needed to the device emulation code. The
+rest of this section is a discussion of how a proxy object model would
+work.
+
+Remote emulation processes
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The remote emulation process will run the QEMU object hierarchy without
+modification. The device emulation objects will be also be based on the
+QEMU code, because for anything but the simplest device, it would not be
+a tractable to re-implement both the object model and the many device
+backends that QEMU has.
+
+The processes will communicate with the QEMU process over UNIX domain
+sockets. The processes can be executed either as standalone processes,
+or be executed by QEMU. In both cases, the host backends the emulation
+processes will provide are specified on its command line, as they would
+be for QEMU. For example:
+
+::
+
+    disk-proc -blockdev driver=file,node-name=file0,filename=disk-file0  \
+    -blockdev driver=qcow2,node-name=drive0,file=file0
+
+would indicate process *disk-proc* uses a qcow2 emulated disk named
+*file0* as its backend.
+
+Emulation processes may emulate more than one guest controller. A common
+configuration might be to put all controllers of the same device class
+(e.g., disk, network, etc.) in a single process, so that all backends of
+the same type can be managed by a single QMP monitor.
+
+communication with QEMU
+^^^^^^^^^^^^^^^^^^^^^^^
+
+The first argument to the remote emulation process will be a Unix domain
+socket that connects with the Proxy object. This is a required argument.
+
+::
+
+    disk-proc <socket number> <backend list>
+
+remote process QMP monitor
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Remote emulation processes can be monitored via QMP, similar to QEMU
+itself. The QMP monitor socket is specified the same as for a QEMU
+process:
+
+::
+
+    disk-proc -qmp unix:/tmp/disk-mon,server
+
+can be monitored over the UNIX socket path */tmp/disk-mon*.
+
+QEMU command line
+~~~~~~~~~~~~~~~~~
+
+Each remote device emulated in a remote process on the host is
+represented as a *-device* of type *pci-proxy-dev*. A socket
+sub-option to this option specifies the Unix socket that connects
+to the remote process. An *id* sub-option is required, and it should
+be the same id as used in the remote process.
+
+::
+
+    qemu-system-x86_64 ... -device pci-proxy-dev,id=lsi0,socket=3
+
+can be used to add a device emulated in a remote process
+
+
+QEMU management of remote processes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+QEMU is not aware of the type of type of the remote PCI device. It is
+a pass through device as far as QEMU is concerned.
+
+communication with emulation process
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+primary channel
+'''''''''''''''
+
+The primary channel (referred to as com in the code) is used to bootstrap
+the remote process. It is also used to pass on device-agnostic commands
+like reset.
+
+per-device channels
+'''''''''''''''''''
+
+Each remote device communicates with QEMU using a dedicated communication
+channel. The proxy object sets up this channel using the primary
+channel during its initialization.
+
+QEMU device proxy objects
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+QEMU has an object model based on sub-classes inherited from the
+"object" super-class. The sub-classes that are of interest here are the
+"device" and "bus" sub-classes whose child sub-classes make up the
+device tree of a QEMU emulated system.
+
+The proxy object model will use device proxy objects to replace the
+device emulation code within the QEMU process. These objects will live
+in the same place in the object and bus hierarchies as the objects they
+replace. i.e., the proxy object for an LSI SCSI controller will be a
+sub-class of the "pci-device" class, and will have the same PCI bus
+parent and the same SCSI bus child objects as the LSI controller object
+it replaces.
+
+It is worth noting that the same proxy object is used to mediate with
+all types of remote PCI devices.
+
+object initialization
+^^^^^^^^^^^^^^^^^^^^^
+
+The Proxy device objects are initialized in the exact same manner in
+which any other QEMU device would be initialized.
+
+In addition, the Proxy objects perform the following two tasks:
+- Parses the "socket" sub option and connects to the remote process
+using this channel
+- Uses the "id" sub-option to connect to the emulated device on the
+separate process
+
+class\_init
+'''''''''''
+
+The ``class_init()`` method of a proxy object will, in general behave
+similarly to the object it replaces, including setting any static
+properties and methods needed by the proxy.
+
+instance\_init / realize
+''''''''''''''''''''''''
+
+The ``instance_init()`` and ``realize()`` functions would only need to
+perform tasks related to being a proxy, such are registering its own
+MMIO handlers, or creating a child bus that other proxy devices can be
+attached to later.
+
+Other tasks will be device-specific. For example, PCI device objects
+will initialize the PCI config space in order to make a valid PCI device
+tree within the QEMU process.
+
+address space registration
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Most devices are driven by guest device driver accesses to IO addresses
+or ports. The QEMU device emulation code uses QEMU's memory region
+function calls (such as ``memory_region_init_io()``) to add callback
+functions that QEMU will invoke when the guest accesses the device's
+areas of the IO address space. When a guest driver does access the
+device, the VM will exit HW virtualization mode and return to QEMU,
+which will then lookup and execute the corresponding callback function.
+
+A proxy object would need to mirror the memory region calls the actual
+device emulator would perform in its initialization code, but with its
+own callbacks. When invoked by QEMU as a result of a guest IO operation,
+they will forward the operation to the device emulation process.
+
+PCI config space
+^^^^^^^^^^^^^^^^
+
+PCI devices also have a configuration space that can be accessed by the
+guest driver. Guest accesses to this space is not handled by the device
+emulation object, but by its PCI parent object. Much of this space is
+read-only, but certain registers (especially BAR and MSI-related ones)
+need to be propagated to the emulation process.
+
+PCI parent proxy
+''''''''''''''''
+
+One way to propagate guest PCI config accesses is to create a
+"pci-device-proxy" class that can serve as the parent of a PCI device
+proxy object. This class's parent would be "pci-device" and it would
+override the PCI parent's ``config_read()`` and ``config_write()``
+methods with ones that forward these operations to the emulation
+program.
+
+interrupt receipt
+^^^^^^^^^^^^^^^^^
+
+A proxy for a device that generates interrupts will need to create a
+socket to receive interrupt indications from the emulation process. An
+incoming interrupt indication would then be sent up to its bus parent to
+be injected into the guest. For example, a PCI device object may use
+``pci_set_irq()``.
+
+live migration
+^^^^^^^^^^^^^^
+
+The proxy will register to save and restore any *vmstate* it needs over
+a live migration event. The device proxy does not need to manage the
+remote device's *vmstate*; that will be handled by the remote process
+proxy (see below).
+
+QEMU remote device operation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Generic device operations, such as DMA, will be performed by the remote
+process proxy by sending messages to the remote process.
+
+DMA operations
+^^^^^^^^^^^^^^
+
+DMA operations would be handled much like vhost applications do. One of
+the initial messages sent to the emulation process is a guest memory
+table. Each entry in this table consists of a file descriptor and size
+that the emulation process can ``mmap()`` to directly access guest
+memory, similar to ``vhost_user_set_mem_table()``. Note guest memory
+must be backed by file descriptors, such as when QEMU is given the
+*-mem-path* command line option.
+
+IOMMU operations
+^^^^^^^^^^^^^^^^
+
+When the emulated system includes an IOMMU, the remote process proxy in
+QEMU will need to create a socket for IOMMU requests from the emulation
+process. It will handle those requests with an
+``address_space_get_iotlb_entry()`` call. In order to handle IOMMU
+unmaps, the remote process proxy will also register as a listener on the
+device's DMA address space. When an IOMMU memory region is created
+within the DMA address space, an IOMMU notifier for unmaps will be added
+to the memory region that will forward unmaps to the emulation process
+over the IOMMU socket.
+
+device hot-plug via QMP
+^^^^^^^^^^^^^^^^^^^^^^^
+
+An QMP "device\_add" command can add a device emulated by a remote
+process. It will also have "rid" option to the command, just as the
+*-device* command line option does. The remote process may either be one
+started at QEMU startup, or be one added by the "add-process" QMP
+command described above. In either case, the remote process proxy will
+forward the new device's JSON description to the corresponding emulation
+process.
+
+live migration
+^^^^^^^^^^^^^^
+
+The remote process proxy will also register for live migration
+notifications with ``vmstate_register()``. When called to save state,
+the proxy will send the remote process a secondary socket file
+descriptor to save the remote process's device *vmstate* over. The
+incoming byte stream length and data will be saved as the proxy's
+*vmstate*. When the proxy is resumed on its new host, this *vmstate*
+will be extracted, and a secondary socket file descriptor will be sent
+to the new remote process through which it receives the *vmstate* in
+order to restore the devices there.
+
+device emulation in remote process
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The parts of QEMU that the emulation program will need include the
+object model; the memory emulation objects; the device emulation objects
+of the targeted device, and any dependent devices; and, the device's
+backends. It will also need code to setup the machine environment,
+handle requests from the QEMU process, and route machine-level requests
+(such as interrupts or IOMMU mappings) back to the QEMU process.
+
+initialization
+^^^^^^^^^^^^^^
+
+The process initialization sequence will follow the same sequence
+followed by QEMU. It will first initialize the backend objects, then
+device emulation objects. The JSON descriptions sent by the QEMU process
+will drive which objects need to be created.
+
+-  address spaces
+
+Before the device objects are created, the initial address spaces and
+memory regions must be configured with ``memory_map_init()``. This
+creates a RAM memory region object (*system\_memory*) and an IO memory
+region object (*system\_io*).
+
+-  RAM
+
+RAM memory region creation will follow how ``pc_memory_init()`` creates
+them, but must use ``memory_region_init_ram_from_fd()`` instead of
+``memory_region_allocate_system_memory()``. The file descriptors needed
+will be supplied by the guest memory table from above. Those RAM regions
+would then be added to the *system\_memory* memory region with
+``memory_region_add_subregion()``.
+
+-  PCI
+
+IO initialization will be driven by the JSON descriptions sent from the
+QEMU process. For a PCI device, a PCI bus will need to be created with
+``pci_root_bus_new()``, and a PCI memory region will need to be created
+and added to the *system\_memory* memory region with
+``memory_region_add_subregion_overlap()``. The overlap version is
+required for architectures where PCI memory overlaps with RAM memory.
+
+MMIO handling
+^^^^^^^^^^^^^
+
+The device emulation objects will use ``memory_region_init_io()`` to
+install their MMIO handlers, and ``pci_register_bar()`` to associate
+those handlers with a PCI BAR, as they do within QEMU currently.
+
+In order to use ``address_space_rw()`` in the emulation process to
+handle MMIO requests from QEMU, the PCI physical addresses must be the
+same in the QEMU process and the device emulation process. In order to
+accomplish that, guest BAR programming must also be forwarded from QEMU
+to the emulation process.
+
+interrupt injection
+^^^^^^^^^^^^^^^^^^^
+
+When device emulation wants to inject an interrupt into the VM, the
+request climbs the device's bus object hierarchy until the point where a
+bus object knows how to signal the interrupt to the guest. The details
+depend on the type of interrupt being raised.
+
+-  PCI pin interrupts
+
+On x86 systems, there is an emulated IOAPIC object attached to the root
+PCI bus object, and the root PCI object forwards interrupt requests to
+it. The IOAPIC object, in turn, calls the KVM driver to inject the
+corresponding interrupt into the VM. The simplest way to handle this in
+an emulation process would be to setup the root PCI bus driver (via
+``pci_bus_irqs()``) to send a interrupt request back to the QEMU
+process, and have the device proxy object reflect it up the PCI tree
+there.
+
+-  PCI MSI/X interrupts
+
+PCI MSI/X interrupts are implemented in HW as DMA writes to a
+CPU-specific PCI address. In QEMU on x86, a KVM APIC object receives
+these DMA writes, then calls into the KVM driver to inject the interrupt
+into the VM. A simple emulation process implementation would be to send
+the MSI DMA address from QEMU as a message at initialization, then
+install an address space handler at that address which forwards the MSI
+message back to QEMU.
+
+DMA operations
+^^^^^^^^^^^^^^
+
+When a emulation object wants to DMA into or out of guest memory, it
+first must use dma\_memory\_map() to convert the DMA address to a local
+virtual address. The emulation process memory region objects setup above
+will be used to translate the DMA address to a local virtual address the
+device emulation code can access.
+
+IOMMU
+^^^^^
+
+When an IOMMU is in use in QEMU, DMA translation uses IOMMU memory
+regions to translate the DMA address to a guest physical address before
+that physical address can be translated to a local virtual address. The
+emulation process will need similar functionality.
+
+-  IOTLB cache
+
+The emulation process will maintain a cache of recent IOMMU translations
+(the IOTLB). When the translate() callback of an IOMMU memory region is
+invoked, the IOTLB cache will be searched for an entry that will map the
+DMA address to a guest PA. On a cache miss, a message will be sent back
+to QEMU requesting the corresponding translation entry, which be both be
+used to return a guest address and be added to the cache.
+
+-  IOTLB purge
+
+The IOMMU emulation will also need to act on unmap requests from QEMU.
+These happen when the guest IOMMU driver purges an entry from the
+guest's translation table.
+
+live migration
+^^^^^^^^^^^^^^
+
+When a remote process receives a live migration indication from QEMU, it
+will set up a channel using the received file descriptor with
+``qio_channel_socket_new_fd()``. This channel will be used to create a
+*QEMUfile* that can be passed to ``qemu_save_device_state()`` to send
+the process's device state back to QEMU. This method will be reversed on
+restore - the channel will be passed to ``qemu_loadvm_state()`` to
+restore the device state.
+
+Accelerating device emulation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The messages that are required to be sent between QEMU and the emulation
+process can add considerable latency to IO operations. The optimizations
+described below attempt to ameliorate this effect by allowing the
+emulation process to communicate directly with the kernel KVM driver.
+The KVM file descriptors created would be passed to the emulation process
+via initialization messages, much like the guest memory table is done.
+#### MMIO acceleration
+
+Vhost user applications can receive guest virtio driver stores directly
+from KVM. The issue with the eventfd mechanism used by vhost user is
+that it does not pass any data with the event indication, so it cannot
+handle guest loads or guest stores that carry store data. This concept
+could, however, be expanded to cover more cases.
+
+The expanded idea would require a new type of KVM device:
+*KVM\_DEV\_TYPE\_USER*. This device has two file descriptors: a master
+descriptor that QEMU can use for configuration, and a slave descriptor
+that the emulation process can use to receive MMIO notifications. QEMU
+would create both descriptors using the KVM driver, and pass the slave
+descriptor to the emulation process via an initialization message.
+
+data structures
+^^^^^^^^^^^^^^^
+
+-  guest physical range
+
+The guest physical range structure describes the address range that a
+device will respond to. It includes the base and length of the range, as
+well as which bus the range resides on (e.g., on an x86machine, it can
+specify whether the range refers to memory or IO addresses).
+
+A device can have multiple physical address ranges it responds to (e.g.,
+a PCI device can have multiple BARs), so the structure will also include
+an enumerated identifier to specify which of the device's ranges is
+being referred to.
+
++--------+----------------------------+
+| Name   | Description                |
++========+============================+
+| addr   | range base address         |
++--------+----------------------------+
+| len    | range length               |
++--------+----------------------------+
+| bus    | addr type (memory or IO)   |
++--------+----------------------------+
+| id     | range ID (e.g., PCI BAR)   |
++--------+----------------------------+
+
+-  MMIO request structure
+
+This structure describes an MMIO operation. It includes which guest
+physical range the MMIO was within, the offset within that range, the
+MMIO type (e.g., load or store), and its length and data. It also
+includes a sequence number that can be used to reply to the MMIO, and
+the CPU that issued the MMIO.
+
++----------+------------------------+
+| Name     | Description            |
++==========+========================+
+| rid      | range MMIO is within   |
++----------+------------------------+
+| offset   | offset withing *rid*   |
++----------+------------------------+
+| type     | e.g., load or store    |
++----------+------------------------+
+| len      | MMIO length            |
++----------+------------------------+
+| data     | store data             |
++----------+------------------------+
+| seq      | sequence ID            |
++----------+------------------------+
+
+-  MMIO request queues
+
+MMIO request queues are FIFO arrays of MMIO request structures. There
+are two queues: pending queue is for MMIOs that haven't been read by the
+emulation program, and the sent queue is for MMIOs that haven't been
+acknowledged. The main use of the second queue is to validate MMIO
+replies from the emulation program.
+
+-  scoreboard
+
+Each CPU in the VM is emulated in QEMU by a separate thread, so multiple
+MMIOs may be waiting to be consumed by an emulation program and multiple
+threads may be waiting for MMIO replies. The scoreboard would contain a
+wait queue and sequence number for the per-CPU threads, allowing them to
+be individually woken when the MMIO reply is received from the emulation
+program. It also tracks the number of posted MMIO stores to the device
+that haven't been replied to, in order to satisfy the PCI constraint
+that a load to a device will not complete until all previous stores to
+that device have been completed.
+
+-  device shadow memory
+
+Some MMIO loads do not have device side-effects. These MMIOs can be
+completed without sending a MMIO request to the emulation program if the
+emulation program shares a shadow image of the device's memory image
+with the KVM driver.
+
+The emulation program will ask the KVM driver to allocate memory for the
+shadow image, and will then use ``mmap()`` to directly access it. The
+emulation program can control KVM access to the shadow image by sending
+KVM an access map telling it which areas of the image have no
+side-effects (and can be completed immediately), and which require a
+MMIO request to the emulation program. The access map can also inform
+the KVM drive which size accesses are allowed to the image.
+
+master descriptor
+^^^^^^^^^^^^^^^^^
+
+The master descriptor is used by QEMU to configure the new KVM device.
+The descriptor would be returned by the KVM driver when QEMU issues a
+*KVM\_CREATE\_DEVICE* ``ioctl()`` with a *KVM\_DEV\_TYPE\_USER* type.
+
+KVM\_DEV\_TYPE\_USER device ops
+
+
+The *KVM\_DEV\_TYPE\_USER* operations vector will be registered by a
+``kvm_register_device_ops()`` call when the KVM system in initialized by
+``kvm_init()``. These device ops are called by the KVM driver when QEMU
+executes certain ``ioctl()`` operations on its KVM file descriptor. They
+include:
+
+-  create
+
+This routine is called when QEMU issues a *KVM\_CREATE\_DEVICE*
+``ioctl()`` on its per-VM file descriptor. It will allocate and
+initialize a KVM user device specific data structure, and assign the
+*kvm\_device* private field to it.
+
+-  ioctl
+
+This routine is invoked when QEMU issues an ``ioctl()`` on the master
+descriptor. The ``ioctl()`` commands supported are defined by the KVM
+device type. *KVM\_DEV\_TYPE\_USER* ones will need several commands:
+
+*KVM\_DEV\_USER\_SLAVE\_FD* creates the slave file descriptor that will
+be passed to the device emulation program. Only one slave can be created
+by each master descriptor. The file operations performed by this
+descriptor are described below.
+
+The *KVM\_DEV\_USER\_PA\_RANGE* command configures a guest physical
+address range that the slave descriptor will receive MMIO notifications
+for. The range is specified by a guest physical range structure
+argument. For buses that assign addresses to devices dynamically, this
+command can be executed while the guest is running, such as the case
+when a guest changes a device's PCI BAR registers.
+
+*KVM\_DEV\_USER\_PA\_RANGE* will use ``kvm_io_bus_register_dev()`` to
+register *kvm\_io\_device\_ops* callbacks to be invoked when the guest
+performs a MMIO operation within the range. When a range is changed,
+``kvm_io_bus_unregister_dev()`` is used to remove the previous
+instantiation.
+
+*KVM\_DEV\_USER\_TIMEOUT* will configure a timeout value that specifies
+how long KVM will wait for the emulation process to respond to a MMIO
+indication.
+
+-  destroy
+
+This routine is called when the VM instance is destroyed. It will need
+to destroy the slave descriptor; and free any memory allocated by the
+driver, as well as the *kvm\_device* structure itself.
+
+slave descriptor
+^^^^^^^^^^^^^^^^
+
+The slave descriptor will have its own file operations vector, which
+responds to system calls on the descriptor performed by the device
+emulation program.
+
+-  read
+
+A read returns any pending MMIO requests from the KVM driver as MMIO
+request structures. Multiple structures can be returned if there are
+multiple MMIO operations pending. The MMIO requests are moved from the
+pending queue to the sent queue, and if there are threads waiting for
+space in the pending to add new MMIO operations, they will be woken
+here.
+
+-  write
+
+A write also consists of a set of MMIO requests. They are compared to
+the MMIO requests in the sent queue. Matches are removed from the sent
+queue, and any threads waiting for the reply are woken. If a store is
+removed, then the number of posted stores in the per-CPU scoreboard is
+decremented. When the number is zero, and a non side-effect load was
+waiting for posted stores to complete, the load is continued.
+
+-  ioctl
+
+There are several ioctl()s that can be performed on the slave
+descriptor.
+
+A *KVM\_DEV\_USER\_SHADOW\_SIZE* ``ioctl()`` causes the KVM driver to
+allocate memory for the shadow image. This memory can later be
+``mmap()``\ ed by the emulation process to share the emulation's view of
+device memory with the KVM driver.
+
+A *KVM\_DEV\_USER\_SHADOW\_CTRL* ``ioctl()`` controls access to the
+shadow image. It will send the KVM driver a shadow control map, which
+specifies which areas of the image can complete guest loads without
+sending the load request to the emulation program. It will also specify
+the size of load operations that are allowed.
+
+-  poll
+
+An emulation program will use the ``poll()`` call with a *POLLIN* flag
+to determine if there are MMIO requests waiting to be read. It will
+return if the pending MMIO request queue is not empty.
+
+-  mmap
+
+This call allows the emulation program to directly access the shadow
+image allocated by the KVM driver. As device emulation updates device
+memory, changes with no side-effects will be reflected in the shadow,
+and the KVM driver can satisfy guest loads from the shadow image without
+needing to wait for the emulation program.
+
+kvm\_io\_device ops
+^^^^^^^^^^^^^^^^^^^
+
+Each KVM per-CPU thread can handle MMIO operation on behalf of the guest
+VM. KVM will use the MMIO's guest physical address to search for a
+matching *kvm\_io\_device* to see if the MMIO can be handled by the KVM
+driver instead of exiting back to QEMU. If a match is found, the
+corresponding callback will be invoked.
+
+-  read
+
+This callback is invoked when the guest performs a load to the device.
+Loads with side-effects must be handled synchronously, with the KVM
+driver putting the QEMU thread to sleep waiting for the emulation
+process reply before re-starting the guest. Loads that do not have
+side-effects may be optimized by satisfying them from the shadow image,
+if there are no outstanding stores to the device by this CPU. PCI memory
+ordering demands that a load cannot complete before all older stores to
+the same device have been completed.
+
+-  write
+
+Stores can be handled asynchronously unless the pending MMIO request
+queue is full. In this case, the QEMU thread must sleep waiting for
+space in the queue. Stores will increment the number of posted stores in
+the per-CPU scoreboard, in order to implement the PCI ordering
+constraint above.
+
+interrupt acceleration
+^^^^^^^^^^^^^^^^^^^^^^
+
+This performance optimization would work much like a vhost user
+application does, where the QEMU process sets up *eventfds* that cause
+the device's corresponding interrupt to be triggered by the KVM driver.
+These irq file descriptors are sent to the emulation process at
+initialization, and are used when the emulation code raises a device
+interrupt.
+
+intx acceleration
+'''''''''''''''''
+
+Traditional PCI pin interrupts are level based, so, in addition to an
+irq file descriptor, a re-sampling file descriptor needs to be sent to
+the emulation program. This second file descriptor allows multiple
+devices sharing an irq to be notified when the interrupt has been
+acknowledged by the guest, so they can re-trigger the interrupt if their
+device has not de-asserted its interrupt.
+
+intx irq descriptor
+
+
+The irq descriptors are created by the proxy object
+``using event_notifier_init()`` to create the irq and re-sampling
+*eventds*, and ``kvm_vm_ioctl(KVM_IRQFD)`` to bind them to an interrupt.
+The interrupt route can be found with
+``pci_device_route_intx_to_irq()``.
+
+intx routing changes
+
+
+Intx routing can be changed when the guest programs the APIC the device
+pin is connected to. The proxy object in QEMU will use
+``pci_device_set_intx_routing_notifier()`` to be informed of any guest
+changes to the route. This handler will broadly follow the VFIO
+interrupt logic to change the route: de-assigning the existing irq
+descriptor from its route, then assigning it the new route. (see
+``vfio_intx_update()``)
+
+MSI/X acceleration
+''''''''''''''''''
+
+MSI/X interrupts are sent as DMA transactions to the host. The interrupt
+data contains a vector that is programmed by the guest, A device may have
+multiple MSI interrupts associated with it, so multiple irq descriptors
+may need to be sent to the emulation program.
+
+MSI/X irq descriptor
+
+
+This case will also follow the VFIO example. For each MSI/X interrupt,
+an *eventfd* is created, a virtual interrupt is allocated by
+``kvm_irqchip_add_msi_route()``, and the virtual interrupt is bound to
+the eventfd with ``kvm_irqchip_add_irqfd_notifier()``.
+
+MSI/X config space changes
+
+
+The guest may dynamically update several MSI-related tables in the
+device's PCI config space. These include per-MSI interrupt enables and
+vector data. Additionally, MSIX tables exist in device memory space, not
+config space. Much like the BAR case above, the proxy object must look
+at guest config space programming to keep the MSI interrupt state
+consistent between QEMU and the emulation program.
+
+--------------
+
+Disaggregated CPU emulation
+---------------------------
+
+After IO services have been disaggregated, a second phase would be to
+separate a process to handle CPU instruction emulation from the main
+QEMU control function. There are no object separation points for this
+code, so the first task would be to create one.
+
+Host access controls
+--------------------
+
+Separating QEMU relies on the host OS's access restriction mechanisms to
+enforce that the differing processes can only access the objects they
+are entitled to. There are a couple types of mechanisms usually provided
+by general purpose OSs.
+
+Discretionary access control
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Discretionary access control allows each user to control who can access
+their files. In Linux, this type of control is usually too coarse for
+QEMU separation, since it only provides three separate access controls:
+one for the same user ID, the second for users IDs with the same group
+ID, and the third for all other user IDs. Each device instance would
+need a separate user ID to provide access control, which is likely to be
+unwieldy for dynamically created VMs.
+
+Mandatory access control
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Mandatory access control allows the OS to add an additional set of
+controls on top of discretionary access for the OS to control. It also
+adds other attributes to processes and files such as types, roles, and
+categories, and can establish rules for how processes and files can
+interact.
+
+Type enforcement
+^^^^^^^^^^^^^^^^
+
+Type enforcement assigns a *type* attribute to processes and files, and
+allows rules to be written on what operations a process with a given
+type can perform on a file with a given type. QEMU separation could take
+advantage of type enforcement by running the emulation processes with
+different types, both from the main QEMU process, and from the emulation
+processes of different classes of devices.
+
+For example, guest disk images and disk emulation processes could have
+types separate from the main QEMU process and non-disk emulation
+processes, and the type rules could prevent processes other than disk
+emulation ones from accessing guest disk images. Similarly, network
+emulation processes can have a type separate from the main QEMU process
+and non-network emulation process, and only that type can access the
+host tun/tap device used to provide guest networking.
+
+Category enforcement
+^^^^^^^^^^^^^^^^^^^^
+
+Category enforcement assigns a set of numbers within a given range to
+the process or file. The process is granted access to the file if the
+process's set is a superset of the file's set. This enforcement can be
+used to separate multiple instances of devices in the same class.
+
+For example, if there are multiple disk devices provides to a guest,
+each device emulation process could be provisioned with a separate
+category. The different device emulation processes would not be able to
+access each other's backing disk images.
+
+Alternatively, categories could be used in lieu of the type enforcement
+scheme described above. In this scenario, different categories would be
+used to prevent device emulation processes in different classes from
+accessing resources assigned to other classes.
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Adds documentation explaining the command-line arguments needed
to use multi-process.

[Move orphan docs/multi-process.rst document into docs/system/ and add
it to index.rst to prevent Sphinx "document isn't included in any
toctree" error.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                   |  1 +
 docs/system/index.rst         |  1 +
 docs/system/multi-process.rst | 64 +++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+)
 create mode 100644 docs/system/multi-process.rst

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ M: Jagannathan Raman <jag.raman@oracle.com>
 M: John G Johnson <john.g.johnson@oracle.com>
 S: Maintained
 F: docs/devel/multi-process.rst
+F: docs/system/multi-process.rst
 
 Build and test automation
 -------------------------
diff --git a/docs/system/index.rst b/docs/system/index.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/index.rst
+++ b/docs/system/index.rst
@@ -XXX,XX +XXX,XX @@ Contents:
    pr-manager
    targets
    security
+   multi-process
    deprecated
    removed-features
    build-platforms
diff --git a/docs/system/multi-process.rst b/docs/system/multi-process.rst
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/docs/system/multi-process.rst
@@ -XXX,XX +XXX,XX @@
+Multi-process QEMU
+==================
+
+This document describes how to configure and use multi-process qemu.
+For the design document refer to docs/devel/qemu-multiprocess.
+
+1) Configuration
+----------------
+
+multi-process is enabled by default for targets that enable KVM
+
+
+2) Usage
+--------
+
+Multi-process QEMU requires an orchestrator to launch.
+
+Following is a description of command-line used to launch mpqemu.
+
+* Orchestrator:
+
+  - The Orchestrator creates a unix socketpair
+
+  - It launches the remote process and passes one of the
+    sockets to it via command-line.
+
+  - It then launches QEMU and specifies the other socket as an option
+    to the Proxy device object
+
+* Remote Process:
+
+  - QEMU can enter remote process mode by using the "remote" machine
+    option.
+
+  - The orchestrator creates a "remote-object" with details about
+    the device and the file descriptor for the device
+
+  - The remaining options are no different from how one launches QEMU with
+    devices.
+
+  - Example command-line for the remote process is as follows:
+
+      /usr/bin/qemu-system-x86_64                                        \
+      -machine x-remote                                                  \
+      -device lsi53c895a,id=lsi0                                         \
+      -drive id=drive_image2,file=/build/ol7-nvme-test-1.qcow2           \
+      -device scsi-hd,id=drive2,drive=drive_image2,bus=lsi0.0,scsi-id=0  \
+      -object x-remote-object,id=robj1,devid=lsi1,fd=4,
+
+* QEMU:
+
+  - Since parts of the RAM are shared between QEMU & remote process, a
+    memory-backend-memfd is required to facilitate this, as follows:
+
+    -object memory-backend-memfd,id=mem,size=2G
+
+  - A "x-pci-proxy-dev" device is created for each of the PCI devices emulated
+    in the remote process. A "socket" sub-option specifies the other end of
+    unix channel created by orchestrator. The "id" sub-option must be specified
+    and should be the same as the "id" specified for the remote PCI device
+
+  - Example commandline for QEMU is as follows:
+
+      -device x-pci-proxy-dev,id=lsi0,socket=3
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Allow RAM MemoryRegion to be created from an offset in a file, instead
of allocating at offset of 0 by default. This is needed to synchronize
RAM between QEMU & remote process.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 609996697ad8617e3b01df38accc5c208c24d74e.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/exec/memory.h     |  2 ++
 include/exec/ram_addr.h   |  4 ++--
 include/qemu/mmap-alloc.h |  4 +++-
 backends/hostmem-memfd.c  |  2 +-
 hw/misc/ivshmem.c         |  3 ++-
 softmmu/memory.c          |  3 ++-
 softmmu/physmem.c         | 12 +++++++-----
 util/mmap-alloc.c         |  8 +++++---
 util/oslib-posix.c        |  2 +-
 9 files changed, 25 insertions(+), 15 deletions(-)

diff --git a/include/exec/memory.h b/include/exec/memory.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
  * @size: size of the region.
  * @share: %true if memory must be mmaped with the MAP_SHARED flag
  * @fd: the fd to mmap.
+ * @offset: offset within the file referenced by fd
  * @errp: pointer to Error*, to store an error if it happens.
  *
  * Note that this function does not do anything to cause the data in the
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
                                     uint64_t size,
                                     bool share,
                                     int fd,
+                                    ram_addr_t offset,
                                     Error **errp);
 #endif
 
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
                                    uint32_t ram_flags, const char *mem_path,
                                    bool readonly, Error **errp);
 RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
-                                 uint32_t ram_flags, int fd, bool readonly,
-                                 Error **errp);
+                                 uint32_t ram_flags, int fd, off_t offset,
+                                 bool readonly, Error **errp);
 
 RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
                                   MemoryRegion *mr, Error **errp);
diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h
index XXXXXXX..XXXXXXX 100644
--- a/include/qemu/mmap-alloc.h
+++ b/include/qemu/mmap-alloc.h
@@ -XXX,XX +XXX,XX @@ size_t qemu_mempath_getpagesize(const char *mem_path);
  *  @readonly: true for a read-only mapping, false for read/write.
  *  @shared: map has RAM_SHARED flag.
  *  @is_pmem: map has RAM_PMEM flag.
+ *  @map_offset: map starts at offset of map_offset from the start of fd
  *
  * Return:
  *  On success, return a pointer to the mapped area.
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
                     size_t align,
                     bool readonly,
                     bool shared,
-                    bool is_pmem);
+                    bool is_pmem,
+                    off_t map_offset);
 
 void qemu_ram_munmap(int fd, void *ptr, size_t size);
 
diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c
index XXXXXXX..XXXXXXX 100644
--- a/backends/hostmem-memfd.c
+++ b/backends/hostmem-memfd.c
@@ -XXX,XX +XXX,XX @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
     name = host_memory_backend_get_name(backend);
     memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend),
                                    name, backend->size,
-                                   backend->share, fd, errp);
+                                   backend->share, fd, 0, errp);
     g_free(name);
 }
 
diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/ivshmem.c
+++ b/hw/misc/ivshmem.c
@@ -XXX,XX +XXX,XX @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp)
 
     /* mmap the region and map into the BAR2 */
     memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s),
-                                   "ivshmem.bar2", size, true, fd, &local_err);
+                                   "ivshmem.bar2", size, true, fd, 0,
+                                   &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         return;
diff --git a/softmmu/memory.c b/softmmu/memory.c
index XXXXXXX..XXXXXXX 100644
--- a/softmmu/memory.c
+++ b/softmmu/memory.c
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
                                     uint64_t size,
                                     bool share,
                                     int fd,
+                                    ram_addr_t offset,
                                     Error **errp)
 {
     Error *err = NULL;
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
     mr->destructor = memory_region_destructor_ram;
     mr->ram_block = qemu_ram_alloc_from_fd(size, mr,
                                            share ? RAM_SHARED : 0,
-                                           fd, false, &err);
+                                           fd, offset, false, &err);
     if (err) {
         mr->size = int128_zero();
         object_unparent(OBJECT(mr));
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index XXXXXXX..XXXXXXX 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block,
                             int fd,
                             bool readonly,
                             bool truncate,
+                            off_t offset,
                             Error **errp)
 {
     void *area;
@@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block,
     }
 
     area = qemu_ram_mmap(fd, memory, block->mr->align, readonly,
-                         block->flags & RAM_SHARED, block->flags & RAM_PMEM);
+                         block->flags & RAM_SHARED, block->flags & RAM_PMEM,
+                         offset);
     if (area == MAP_FAILED) {
         error_setg_errno(errp, errno,
                          "unable to map backing store for guest RAM");
@@ -XXX,XX +XXX,XX @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
 
 #ifdef CONFIG_POSIX
 RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
-                                 uint32_t ram_flags, int fd, bool readonly,
-                                 Error **errp)
+                                 uint32_t ram_flags, int fd, off_t offset,
+                                 bool readonly, Error **errp)
 {
     RAMBlock *new_block;
     Error *local_err = NULL;
@@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     new_block->max_length = size;
     new_block->flags = ram_flags;
     new_block->host = file_ram_alloc(new_block, size, fd, readonly,
-                                     !file_size, errp);
+                                     !file_size, offset, errp);
     if (!new_block->host) {
         g_free(new_block);
         return NULL;
@@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
         return NULL;
     }
 
-    block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, readonly, errp);
+    block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, 0, readonly, errp);
     if (!block) {
         if (created) {
             unlink(mem_path);
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index XXXXXXX..XXXXXXX 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
                     size_t align,
                     bool readonly,
                     bool shared,
-                    bool is_pmem)
+                    bool is_pmem,
+                    off_t map_offset)
 {
     int prot;
     int flags;
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
 
     prot = PROT_READ | (readonly ? 0 : PROT_WRITE);
 
-    ptr = mmap(guardptr + offset, size, prot, flags | map_sync_flags, fd, 0);
+    ptr = mmap(guardptr + offset, size, prot,
+               flags | map_sync_flags, fd, map_offset);
 
     if (ptr == MAP_FAILED && map_sync_flags) {
         if (errno == ENOTSUP) {
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
          * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC,
          * we will remove these flags to handle compatibility.
          */
-        ptr = mmap(guardptr + offset, size, prot, flags, fd, 0);
+        ptr = mmap(guardptr + offset, size, prot, flags, fd, map_offset);
     }
 
     if (ptr == MAP_FAILED) {
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index XXXXXXX..XXXXXXX 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -XXX,XX +XXX,XX @@ void *qemu_memalign(size_t alignment, size_t size)
 void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared)
 {
     size_t align = QEMU_VMALLOC_ALIGN;
-    void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false);
+    void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false, 0);
 
     if (ptr == MAP_FAILED) {
         return NULL;
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Add configuration options to enable or disable multiprocess QEMU code

diff --git a/configure b/configure
index XXXXXXX..XXXXXXX 100755
--- a/configure
+++ b/configure
@@ -XXX,XX +XXX,XX @@ skip_meson=no
 gettext="auto"
 fuse="auto"
 fuse_lseek="auto"
+multiprocess="no"
 
 malloc_trim="auto"
 
@@ -XXX,XX +XXX,XX @@ Linux)
   linux="yes"
   linux_user="yes"
   vhost_user=${default_feature:-yes}
+  multiprocess=${default_feature:-yes}
 ;;
 esac
 
@@ -XXX,XX +XXX,XX @@ for opt do
   ;;
   --disable-fuse-lseek) fuse_lseek="disabled"
   ;;
+  --enable-multiprocess) multiprocess="yes"
+  ;;
+  --disable-multiprocess) multiprocess="no"
+  ;;
   *)
       echo "ERROR: unknown option $opt"
       echo "Try '$0 --help' for more information"
@@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available
   libdaxctl       libdaxctl support
   fuse            FUSE block device export
   fuse-lseek      SEEK_HOLE/SEEK_DATA support for FUSE exports
+  multiprocess    Multiprocess QEMU support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -XXX,XX +XXX,XX @@ fi
 if test "$have_mlockall" = "yes" ; then
   echo "HAVE_MLOCKALL=y" >> $config_host_mak
 fi
+if test "$multiprocess" = "yes" ; then
+  echo "CONFIG_MULTIPROCESS_ALLOWED=y" >> $config_host_mak
+fi
 if test "$fuzzing" = "yes" ; then
   # If LIB_FUZZING_ENGINE is set, assume we are running on OSS-Fuzz, and the
   # needed CFLAGS have already been provided
diff --git a/meson.build b/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/meson.build
+++ b/meson.build
@@ -XXX,XX +XXX,XX @@ host_kconfig = \
   ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \
   (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \
   ('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \
-  ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : [])
+  ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \
+  ('CONFIG_MULTIPROCESS_ALLOWED' in config_host ? ['CONFIG_MULTIPROCESS_ALLOWED=y'] : [])
 
 ignored = [ 'TARGET_XML_FILES', 'TARGET_ABI_DIR', 'TARGET_ARCH' ]
 
@@ -XXX,XX +XXX,XX @@ summary_info += {'libpmem support':   config_host.has_key('CONFIG_LIBPMEM')}
 summary_info += {'libdaxctl support': config_host.has_key('CONFIG_LIBDAXCTL')}
 summary_info += {'libudev':           libudev.found()}
 summary_info += {'FUSE lseek':        fuse_lseek.found()}
+summary_info += {'Multiprocess QEMU': config_host.has_key('CONFIG_MULTIPROCESS_ALLOWED')}
 summary(summary_info, bool_yn: true, section: 'Dependencies')
 
 if not supported_cpus.contains(cpu)
diff --git a/Kconfig.host b/Kconfig.host
index XXXXXXX..XXXXXXX 100644
--- a/Kconfig.host
+++ b/Kconfig.host
@@ -XXX,XX +XXX,XX @@ config VIRTFS
 
 config PVRDMA
     bool
+
+config MULTIPROCESS_ALLOWED
+    bool
+    imply MULTIPROCESS
diff --git a/hw/Kconfig b/hw/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/Kconfig
+++ b/hw/Kconfig
@@ -XXX,XX +XXX,XX @@ source pci-host/Kconfig
 source pcmcia/Kconfig
 source pci/Kconfig
 source rdma/Kconfig
+source remote/Kconfig
 source rtc/Kconfig
 source scsi/Kconfig
 source sd/Kconfig
diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/Kconfig
@@ -XXX,XX +XXX,XX @@
+config MULTIPROCESS
+    bool
+    depends on PCI && KVM
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

PCI host bridge is setup for the remote device process. It is
implemented using remote-pcihost object. It is an extension of the PCI
host bridge setup by QEMU.
Remote-pcihost configures a PCI bus which could be used by the remote
PCI device to latch on to.

[Added PCI_EXPRESS condition in hw/remote/Kconfig since remote-pcihost
needs PCIe. This solves "make check" failure on s390x. Fix suggested by
Philippe Mathieu-Daudé <philmd@redhat.com> and Thomas Huth
<thuth@redhat.com>.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                  |  2 +
 include/hw/pci-host/remote.h | 29 ++++++++++++++
 hw/pci-host/remote.c         | 75 ++++++++++++++++++++++++++++++++++++
 hw/pci-host/Kconfig          |  3 ++
 hw/pci-host/meson.build      |  1 +
 hw/remote/Kconfig            |  3 +-
 6 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 include/hw/pci-host/remote.h
 create mode 100644 hw/pci-host/remote.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ M: John G Johnson <john.g.johnson@oracle.com>
 S: Maintained
 F: docs/devel/multi-process.rst
 F: docs/system/multi-process.rst
+F: hw/pci-host/remote.c
+F: include/hw/pci-host/remote.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/pci-host/remote.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * PCI Host for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef REMOTE_PCIHOST_H
+#define REMOTE_PCIHOST_H
+
+#include "exec/memory.h"
+#include "hw/pci/pcie_host.h"
+
+#define TYPE_REMOTE_PCIHOST "remote-pcihost"
+OBJECT_DECLARE_SIMPLE_TYPE(RemotePCIHost, REMOTE_PCIHOST)
+
+struct RemotePCIHost {
+    /*< private >*/
+    PCIExpressHost parent_obj;
+    /*< public >*/
+
+    MemoryRegion *mr_pci_mem;
+    MemoryRegion *mr_sys_io;
+};
+
+#endif
diff --git a/hw/pci-host/remote.c b/hw/pci-host/remote.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/pci-host/remote.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Remote PCI host device
+ *
+ * Unlike PCI host devices that model physical hardware, the purpose
+ * of this PCI host is to host multi-process QEMU devices.
+ *
+ * Multi-process QEMU extends the PCI host of a QEMU machine into a
+ * remote process. Any PCI device attached to the remote process is
+ * visible in the QEMU guest. This allows existing QEMU device models
+ * to be reused in the remote process.
+ *
+ * This PCI host is purely a container for PCI devices. It's fake in the
+ * sense that the guest never sees this PCI host and has no way of
+ * accessing it. Its job is just to provide the environment that QEMU
+ * PCI device models need when running in a remote process.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_host.h"
+#include "hw/pci/pcie_host.h"
+#include "hw/qdev-properties.h"
+#include "hw/pci-host/remote.h"
+#include "exec/memory.h"
+
+static const char *remote_pcihost_root_bus_path(PCIHostState *host_bridge,
+                                                PCIBus *rootbus)
+{
+    return "0000:00";
+}
+
+static void remote_pcihost_realize(DeviceState *dev, Error **errp)
+{
+    PCIHostState *pci = PCI_HOST_BRIDGE(dev);
+    RemotePCIHost *s = REMOTE_PCIHOST(dev);
+
+    pci->bus = pci_root_bus_new(DEVICE(s), "remote-pci",
+                                s->mr_pci_mem, s->mr_sys_io,
+                                0, TYPE_PCIE_BUS);
+}
+
+static void remote_pcihost_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass);
+
+    hc->root_bus_path = remote_pcihost_root_bus_path;
+    dc->realize = remote_pcihost_realize;
+
+    dc->user_creatable = false;
+    set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+    dc->fw_name = "pci";
+}
+
+static const TypeInfo remote_pcihost_info = {
+    .name = TYPE_REMOTE_PCIHOST,
+    .parent = TYPE_PCIE_HOST_BRIDGE,
+    .instance_size = sizeof(RemotePCIHost),
+    .class_init = remote_pcihost_class_init,
+};
+
+static void remote_pcihost_register(void)
+{
+    type_register_static(&remote_pcihost_info);
+}
+
+type_init(remote_pcihost_register)
diff --git a/hw/pci-host/Kconfig b/hw/pci-host/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/Kconfig
+++ b/hw/pci-host/Kconfig
@@ -XXX,XX +XXX,XX @@ config PCI_POWERNV
     select PCI_EXPRESS
     select MSI_NONBROKEN
     select PCIE_PORT
+
+config REMOTE_PCIHOST
+    bool
diff --git a/hw/pci-host/meson.build b/hw/pci-host/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/meson.build
+++ b/hw/pci-host/meson.build
@@ -XXX,XX +XXX,XX @@ pci_ss.add(when: 'CONFIG_PCI_EXPRESS_XILINX', if_true: files('xilinx-pcie.c'))
 pci_ss.add(when: 'CONFIG_PCI_I440FX', if_true: files('i440fx.c'))
 pci_ss.add(when: 'CONFIG_PCI_SABRE', if_true: files('sabre.c'))
 pci_ss.add(when: 'CONFIG_XEN_IGD_PASSTHROUGH', if_true: files('xen_igd_pt.c'))
+pci_ss.add(when: 'CONFIG_REMOTE_PCIHOST', if_true: files('remote.c'))
 
 # PPC devices
 pci_ss.add(when: 'CONFIG_PREP_PCI', if_true: files('prep.c'))
diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/Kconfig
+++ b/hw/remote/Kconfig
@@ -XXX,XX +XXX,XX @@
 config MULTIPROCESS
     bool
-    depends on PCI && KVM
+    depends on PCI && PCI_EXPRESS && KVM
+    select REMOTE_PCIHOST
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

x-remote-machine object sets up various subsystems of the remote
device process. Instantiate PCI host bridge object and initialize RAM, IO &
PCI memory regions.

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: c537f38d17f90453ca610c6b70cf3480274e0ba1.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                  |  2 ++
 include/hw/pci-host/remote.h |  1 +
 include/hw/remote/machine.h  | 27 ++++++++++++++
 hw/remote/machine.c          | 70 ++++++++++++++++++++++++++++++++++++
 hw/meson.build               |  1 +
 hw/remote/meson.build        |  5 +++
 6 files changed, 106 insertions(+)
 create mode 100644 include/hw/remote/machine.h
 create mode 100644 hw/remote/machine.c
 create mode 100644 hw/remote/meson.build

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: docs/devel/multi-process.rst
 F: docs/system/multi-process.rst
 F: hw/pci-host/remote.c
 F: include/hw/pci-host/remote.h
+F: hw/remote/machine.c
+F: include/hw/remote/machine.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/pci-host/remote.h
+++ b/include/hw/pci-host/remote.h
@@ -XXX,XX +XXX,XX @@ struct RemotePCIHost {
 
     MemoryRegion *mr_pci_mem;
     MemoryRegion *mr_sys_io;
+    MemoryRegion *mr_sys_mem;
 };
 
 #endif
diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/machine.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Remote machine configuration
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef REMOTE_MACHINE_H
+#define REMOTE_MACHINE_H
+
+#include "qom/object.h"
+#include "hw/boards.h"
+#include "hw/pci-host/remote.h"
+
+struct RemoteMachineState {
+    MachineState parent_obj;
+
+    RemotePCIHost *host;
+};
+
+#define TYPE_REMOTE_MACHINE "x-remote-machine"
+OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE)
+
+#endif
diff --git a/hw/remote/machine.c b/hw/remote/machine.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/machine.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Machine for remote device
+ *
+ *  This machine type is used by the remote device process in multi-process
+ *  QEMU. QEMU device models depend on parent busses, interrupt controllers,
+ *  memory regions, etc. The remote machine type offers this environment so
+ *  that QEMU device models can be used as remote devices.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/remote/machine.h"
+#include "exec/address-spaces.h"
+#include "exec/memory.h"
+#include "qapi/error.h"
+
+static void remote_machine_init(MachineState *machine)
+{
+    MemoryRegion *system_memory, *system_io, *pci_memory;
+    RemoteMachineState *s = REMOTE_MACHINE(machine);
+    RemotePCIHost *rem_host;
+
+    system_memory = get_system_memory();
+    system_io = get_system_io();
+
+    pci_memory = g_new(MemoryRegion, 1);
+    memory_region_init(pci_memory, NULL, "pci", UINT64_MAX);
+
+    rem_host = REMOTE_PCIHOST(qdev_new(TYPE_REMOTE_PCIHOST));
+
+    rem_host->mr_pci_mem = pci_memory;
+    rem_host->mr_sys_mem = system_memory;
+    rem_host->mr_sys_io = system_io;
+
+    s->host = rem_host;
+
+    object_property_add_child(OBJECT(s), "remote-pcihost", OBJECT(rem_host));
+    memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1);
+
+    qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal);
+}
+
+static void remote_machine_class_init(ObjectClass *oc, void *data)
+{
+    MachineClass *mc = MACHINE_CLASS(oc);
+
+    mc->init = remote_machine_init;
+    mc->desc = "Experimental remote machine";
+}
+
+static const TypeInfo remote_machine = {
+    .name = TYPE_REMOTE_MACHINE,
+    .parent = TYPE_MACHINE,
+    .instance_size = sizeof(RemoteMachineState),
+    .class_init = remote_machine_class_init,
+};
+
+static void remote_machine_register_types(void)
+{
+    type_register_static(&remote_machine);
+}
+
+type_init(remote_machine_register_types);
diff --git a/hw/meson.build b/hw/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/meson.build
+++ b/hw/meson.build
@@ -XXX,XX +XXX,XX @@ subdir('moxie')
 subdir('nios2')
 subdir('openrisc')
 subdir('ppc')
+subdir('remote')
 subdir('riscv')
 subdir('rx')
 subdir('s390x')
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@
+remote_ss = ss.source_set()
+
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
+
+softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Adds qio_channel_writev_full_all() to transmit both data and FDs.
Refactors existing code to use this helper.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 480fbf1fe4152495d60596c9b665124549b426a5.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/io/channel.h | 25 +++++++++++++++++++++++++
 io/channel.c         | 15 ++++++++++++++-
 2 files changed, 39 insertions(+), 1 deletion(-)

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Adds qio_channel_readv_full_all_eof() and qio_channel_readv_full_all()
to read both data and FDs. Refactors existing code to use these helpers.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: b059c4cc0fb741e794d644c144cc21372cad877d.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/io/channel.h |  53 +++++++++++++++++++++++
 io/channel.c         | 101 ++++++++++++++++++++++++++++++++++---------
 2 files changed, 134 insertions(+), 20 deletions(-)

diff --git a/include/io/channel.h b/include/io/channel.h
index XXXXXXX..XXXXXXX 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -XXX,XX +XXX,XX @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc,
                                     IOHandler *io_write,
                                     void *opaque);
 
+/**
+ * qio_channel_readv_full_all_eof:
+ * @ioc: the channel object
+ * @iov: the array of memory regions to read data to
+ * @niov: the length of the @iov array
+ * @fds: an array of file handles to read
+ * @nfds: number of file handles in @fds
+ * @errp: pointer to a NULL-initialized error object
+ *
+ *
+ * Performs same function as qio_channel_readv_all_eof.
+ * Additionally, attempts to read file descriptors shared
+ * over the channel. The function will wait for all
+ * requested data to be read, yielding from the current
+ * coroutine if required. data refers to both file
+ * descriptors and the iovs.
+ *
+ * Returns: 1 if all bytes were read, 0 if end-of-file
+ *          occurs without data, or -1 on error
+ */
+
+int qio_channel_readv_full_all_eof(QIOChannel *ioc,
+                                   const struct iovec *iov,
+                                   size_t niov,
+                                   int **fds, size_t *nfds,
+                                   Error **errp);
+
+/**
+ * qio_channel_readv_full_all:
+ * @ioc: the channel object
+ * @iov: the array of memory regions to read data to
+ * @niov: the length of the @iov array
+ * @fds: an array of file handles to read
+ * @nfds: number of file handles in @fds
+ * @errp: pointer to a NULL-initialized error object
+ *
+ *
+ * Performs same function as qio_channel_readv_all_eof.
+ * Additionally, attempts to read file descriptors shared
+ * over the channel. The function will wait for all
+ * requested data to be read, yielding from the current
+ * coroutine if required. data refers to both file
+ * descriptors and the iovs.
+ *
+ * Returns: 0 if all bytes were read, or -1 on error
+ */
+
+int qio_channel_readv_full_all(QIOChannel *ioc,
+                               const struct iovec *iov,
+                               size_t niov,
+                               int **fds, size_t *nfds,
+                               Error **errp);
+
 /**
  * qio_channel_writev_full_all:
  * @ioc: the channel object
diff --git a/io/channel.c b/io/channel.c
index XXXXXXX..XXXXXXX 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc,
                               const struct iovec *iov,
                               size_t niov,
                               Error **errp)
+{
+    return qio_channel_readv_full_all_eof(ioc, iov, niov, NULL, NULL, errp);
+}
+
+int qio_channel_readv_all(QIOChannel *ioc,
+                          const struct iovec *iov,
+                          size_t niov,
+                          Error **errp)
+{
+    return qio_channel_readv_full_all(ioc, iov, niov, NULL, NULL, errp);
+}
+
+int qio_channel_readv_full_all_eof(QIOChannel *ioc,
+                                   const struct iovec *iov,
+                                   size_t niov,
+                                   int **fds, size_t *nfds,
+                                   Error **errp)
 {
     int ret = -1;
     struct iovec *local_iov = g_new(struct iovec, niov);
     struct iovec *local_iov_head = local_iov;
     unsigned int nlocal_iov = niov;
+    int **local_fds = fds;
+    size_t *local_nfds = nfds;
     bool partial = false;
 
+    if (nfds) {
+        *nfds = 0;
+    }
+
+    if (fds) {
+        *fds = NULL;
+    }
+
     nlocal_iov = iov_copy(local_iov, nlocal_iov,
                           iov, niov,
                           0, iov_size(iov, niov));
 
-    while (nlocal_iov > 0) {
+    while ((nlocal_iov > 0) || local_fds) {
         ssize_t len;
-        len = qio_channel_readv(ioc, local_iov, nlocal_iov, errp);
+        len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds,
+                                     local_nfds, errp);
         if (len == QIO_CHANNEL_ERR_BLOCK) {
             if (qemu_in_coroutine()) {
                 qio_channel_yield(ioc, G_IO_IN);
@@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc,
                 qio_channel_wait(ioc, G_IO_IN);
             }
             continue;
-        } else if (len < 0) {
-            goto cleanup;
-        } else if (len == 0) {
-            if (partial) {
-                error_setg(errp,
-                           "Unexpected end-of-file before all bytes were read");
-            } else {
+        }
+
+        if (len == 0) {
+            if (local_nfds && *local_nfds) {
+                /*
+                 * Got some FDs, but no data yet. This isn't an EOF
+                 * scenario (yet), so carry on to try to read data
+                 * on next loop iteration
+                 */
+                goto next_iter;
+            } else if (!partial) {
+                /* No fds and no data - EOF before any data read */
                 ret = 0;
+                goto cleanup;
+            } else {
+                len = -1;
+                error_setg(errp,
+                           "Unexpected end-of-file before all data were read");
+                /* Fallthrough into len < 0 handling */
+            }
+        }
+
+        if (len < 0) {
+            /* Close any FDs we previously received */
+            if (nfds && fds) {
+                size_t i;
+                for (i = 0; i < (*nfds); i++) {
+                    close((*fds)[i]);
+                }
+                g_free(*fds);
+                *fds = NULL;
+                *nfds = 0;
             }
             goto cleanup;
         }
 
+        if (nlocal_iov) {
+            iov_discard_front(&local_iov, &nlocal_iov, len);
+        }
+
+next_iter:
         partial = true;
-        iov_discard_front(&local_iov, &nlocal_iov, len);
+        local_fds = NULL;
+        local_nfds = NULL;
     }
 
     ret = 1;
@@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc,
     return ret;
 }
 
-int qio_channel_readv_all(QIOChannel *ioc,
-                          const struct iovec *iov,
-                          size_t niov,
-                          Error **errp)
+int qio_channel_readv_full_all(QIOChannel *ioc,
+                               const struct iovec *iov,
+                               size_t niov,
+                               int **fds, size_t *nfds,
+                               Error **errp)
 {
-    int ret = qio_channel_readv_all_eof(ioc, iov, niov, errp);
+    int ret = qio_channel_readv_full_all_eof(ioc, iov, niov, fds, nfds, errp);
 
     if (ret == 0) {
-        ret = -1;
-        error_setg(errp,
-                   "Unexpected end-of-file before all bytes were read");
-    } else if (ret == 1) {
-        ret = 0;
+        error_prepend(errp,
+                      "Unexpected end-of-file before all data were read.");
+        return -1;
     }
+    if (ret == 1) {
+        return 0;
+    }
+
     return ret;
 }
 
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Defines MPQemuMsg, which is the message that is sent to the remote
process. This message is sent over QIOChannel and is used to
command the remote process to perform various tasks.
Define transmission functions used by proxy and by remote.

[Replace struct iovec send[2] = {0} with {} to make clang happy as
suggested by Peter Maydell <peter.maydell@linaro.org>.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                     |   2 +
 meson.build                     |   1 +
 hw/remote/trace.h               |   1 +
 include/hw/remote/mpqemu-link.h |  63 ++++++++++
 include/sysemu/iothread.h       |   6 +
 hw/remote/mpqemu-link.c         | 205 ++++++++++++++++++++++++++++++++
 iothread.c                      |   6 +
 hw/remote/meson.build           |   1 +
 hw/remote/trace-events          |   4 +
 9 files changed, 289 insertions(+)
 create mode 100644 hw/remote/trace.h
 create mode 100644 include/hw/remote/mpqemu-link.h
 create mode 100644 hw/remote/mpqemu-link.c
 create mode 100644 hw/remote/trace-events

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/pci-host/remote.c
 F: include/hw/pci-host/remote.h
 F: hw/remote/machine.c
 F: include/hw/remote/machine.h
+F: hw/remote/mpqemu-link.c
+F: include/hw/remote/mpqemu-link.h
 
 Build and test automation
 -------------------------
diff --git a/meson.build b/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/meson.build
+++ b/meson.build
@@ -XXX,XX +XXX,XX @@ if have_system
     'net',
     'softmmu',
     'ui',
+    'hw/remote',
   ]
 endif
 if have_system or have_user
diff --git a/hw/remote/trace.h b/hw/remote/trace.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-hw_remote.h"
diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Communication channel between QEMU and remote device process
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef MPQEMU_LINK_H
+#define MPQEMU_LINK_H
+
+#include "qom/object.h"
+#include "qemu/thread.h"
+#include "io/channel.h"
+
+#define REMOTE_MAX_FDS 8
+
+#define MPQEMU_MSG_HDR_SIZE offsetof(MPQemuMsg, data.u64)
+
+/**
+ * MPQemuCmd:
+ *
+ * MPQemuCmd enum type to specify the command to be executed on the remote
+ * device.
+ *
+ * This uses a private protocol between QEMU and the remote process. vfio-user
+ * protocol would supersede this in the future.
+ *
+ */
+typedef enum {
+    MPQEMU_CMD_MAX,
+} MPQemuCmd;
+
+/**
+ * MPQemuMsg:
+ * @cmd: The remote command
+ * @size: Size of the data to be shared
+ * @data: Structured data
+ * @fds: File descriptors to be shared with remote device
+ *
+ * MPQemuMsg Format of the message sent to the remote device from QEMU.
+ *
+ */
+typedef struct {
+    int cmd;
+    size_t size;
+
+    union {
+        uint64_t u64;
+    } data;
+
+    int fds[REMOTE_MAX_FDS];
+    int num_fds;
+} MPQemuMsg;
+
+bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
+bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
+
+bool mpqemu_msg_valid(MPQemuMsg *msg);
+
+#endif
diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/iothread.h
+++ b/include/sysemu/iothread.h
@@ -XXX,XX +XXX,XX @@ IOThread *iothread_create(const char *id, Error **errp);
 void iothread_stop(IOThread *iothread);
 void iothread_destroy(IOThread *iothread);
 
+/*
+ * Returns true if executing withing IOThread context,
+ * false otherwise.
+ */
+bool qemu_in_iothread(void);
+
 #endif /* IOTHREAD_H */
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Communication channel between QEMU and remote device process
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "qemu/module.h"
+#include "hw/remote/mpqemu-link.h"
+#include "qapi/error.h"
+#include "qemu/iov.h"
+#include "qemu/error-report.h"
+#include "qemu/main-loop.h"
+#include "io/channel.h"
+#include "sysemu/iothread.h"
+#include "trace.h"
+
+/*
+ * Send message over the ioc QIOChannel.
+ * This function is safe to call from:
+ * - main loop in co-routine context. Will block the main loop if not in
+ *   co-routine context;
+ * - vCPU thread with no co-routine context and if the channel is not part
+ *   of the main loop handling;
+ * - IOThread within co-routine context, outside of co-routine context
+ *   will block IOThread;
+ * Returns true if no errors were encountered, false otherwise.
+ */
+bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
+{
+    ERRP_GUARD();
+    bool iolock = qemu_mutex_iothread_locked();
+    bool iothread = qemu_in_iothread();
+    struct iovec send[2] = {};
+    int *fds = NULL;
+    size_t nfds = 0;
+    bool ret = false;
+
+    send[0].iov_base = msg;
+    send[0].iov_len = MPQEMU_MSG_HDR_SIZE;
+
+    send[1].iov_base = (void *)&msg->data;
+    send[1].iov_len = msg->size;
+
+    if (msg->num_fds) {
+        nfds = msg->num_fds;
+        fds = msg->fds;
+    }
+
+    /*
+     * Dont use in IOThread out of co-routine context as
+     * it will block IOThread.
+     */
+    assert(qemu_in_coroutine() || !iothread);
+
+    /*
+     * Skip unlocking/locking iothread lock when the IOThread is running
+     * in co-routine context. Co-routine context is asserted above
+     * for IOThread case.
+     * Also skip lock handling while in a co-routine in the main context.
+     */
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        qemu_mutex_unlock_iothread();
+    }
+
+    if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send),
+                                    fds, nfds, errp)) {
+        ret = true;
+    } else {
+        trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds);
+    }
+
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        /* See above comment why skip locking here. */
+        qemu_mutex_lock_iothread();
+    }
+
+    return ret;
+}
+
+/*
+ * Read message from the ioc QIOChannel.
+ * This function is safe to call from:
+ * - From main loop in co-routine context. Will block the main loop if not in
+ *   co-routine context;
+ * - From vCPU thread with no co-routine context and if the channel is not part
+ *   of the main loop handling;
+ * - From IOThread within co-routine context, outside of co-routine context
+ *   will block IOThread;
+ */
+static ssize_t mpqemu_read(QIOChannel *ioc, void *buf, size_t len, int **fds,
+                           size_t *nfds, Error **errp)
+{
+    ERRP_GUARD();
+    struct iovec iov = { .iov_base = buf, .iov_len = len };
+    bool iolock = qemu_mutex_iothread_locked();
+    bool iothread = qemu_in_iothread();
+    int ret = -1;
+
+    /*
+     * Dont use in IOThread out of co-routine context as
+     * it will block IOThread.
+     */
+    assert(qemu_in_coroutine() || !iothread);
+
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        qemu_mutex_unlock_iothread();
+    }
+
+    ret = qio_channel_readv_full_all_eof(ioc, &iov, 1, fds, nfds, errp);
+
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        qemu_mutex_lock_iothread();
+    }
+
+    return (ret <= 0) ? ret : iov.iov_len;
+}
+
+bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
+{
+    ERRP_GUARD();
+    g_autofree int *fds = NULL;
+    size_t nfds = 0;
+    ssize_t len;
+    bool ret = false;
+
+    len = mpqemu_read(ioc, msg, MPQEMU_MSG_HDR_SIZE, &fds, &nfds, errp);
+    if (len <= 0) {
+        goto fail;
+    } else if (len != MPQEMU_MSG_HDR_SIZE) {
+        error_setg(errp, "Message header corrupted");
+        goto fail;
+    }
+
+    if (msg->size > sizeof(msg->data)) {
+        error_setg(errp, "Invalid size for message");
+        goto fail;
+    }
+
+    if (!msg->size) {
+        goto copy_fds;
+    }
+
+    len = mpqemu_read(ioc, &msg->data, msg->size, NULL, NULL, errp);
+    if (len <= 0) {
+        goto fail;
+    }
+    if (len != msg->size) {
+        error_setg(errp, "Unable to read full message");
+        goto fail;
+    }
+
+copy_fds:
+    msg->num_fds = nfds;
+    if (nfds > G_N_ELEMENTS(msg->fds)) {
+        error_setg(errp,
+                   "Overflow error: received %zu fds, more than max of %d fds",
+                   nfds, REMOTE_MAX_FDS);
+        goto fail;
+    }
+    if (nfds) {
+        memcpy(msg->fds, fds, nfds * sizeof(int));
+    }
+
+    ret = true;
+
+fail:
+    if (*errp) {
+        trace_mpqemu_recv_io_error(msg->cmd, msg->size, nfds);
+    }
+    while (*errp && nfds) {
+        close(fds[nfds - 1]);
+        nfds--;
+    }
+
+    return ret;
+}
+
+bool mpqemu_msg_valid(MPQemuMsg *msg)
+{
+    if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) {
+        return false;
+    }
+
+    /* Verify FDs. */
+    if (msg->num_fds >= REMOTE_MAX_FDS) {
+        return false;
+    }
+
+    if (msg->num_fds > 0) {
+        for (int i = 0; i < msg->num_fds; i++) {
+            if (fcntl(msg->fds[i], F_GETFL) == -1) {
+                return false;
+            }
+        }
+    }
+
+    return true;
+}
diff --git a/iothread.c b/iothread.c
index XXXXXXX..XXXXXXX 100644
--- a/iothread.c
+++ b/iothread.c
@@ -XXX,XX +XXX,XX @@ IOThread *iothread_by_id(const char *id)
 {
     return IOTHREAD(object_resolve_path_type(id, TYPE_IOTHREAD, NULL));
 }
+
+bool qemu_in_iothread(void)
+{
+    return qemu_get_current_aio_context() == qemu_get_aio_context() ?
+                    false : true;
+}
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@
 remote_ss = ss.source_set()
 
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
diff --git a/hw/remote/trace-events b/hw/remote/trace-events
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/trace-events
@@ -XXX,XX +XXX,XX @@
+# multi-process trace events
+
+mpqemu_send_io_error(int cmd, int size, int nfds) "send command %d size %d, %d file descriptors to remote process"
+mpqemu_recv_io_error(int cmd, int size, int nfds) "failed to receive %d size %d, %d file descriptors to remote process"
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Initializes the message handler function in the remote process. It is
called whenever there's an event pending on QIOChannel that registers
this function.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 99d38d8b93753a6409ac2340e858858cda59ab1b.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                 |  1 +
 include/hw/remote/machine.h |  9 ++++++
 hw/remote/message.c         | 57 +++++++++++++++++++++++++++++++++++++
 hw/remote/meson.build       |  1 +
 4 files changed, 68 insertions(+)
 create mode 100644 hw/remote/message.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/machine.c
 F: include/hw/remote/machine.h
 F: hw/remote/mpqemu-link.c
 F: include/hw/remote/mpqemu-link.h
+F: hw/remote/message.c
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/machine.h
+++ b/include/hw/remote/machine.h
@@ -XXX,XX +XXX,XX @@
 #include "qom/object.h"
 #include "hw/boards.h"
 #include "hw/pci-host/remote.h"
+#include "io/channel.h"
 
 struct RemoteMachineState {
     MachineState parent_obj;
@@ -XXX,XX +XXX,XX @@ struct RemoteMachineState {
     RemotePCIHost *host;
 };
 
+/* Used to pass to co-routine device and ioc. */
+typedef struct RemoteCommDev {
+    PCIDevice *dev;
+    QIOChannel *ioc;
+} RemoteCommDev;
+
 #define TYPE_REMOTE_MACHINE "x-remote-machine"
 OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE)
 
+void coroutine_fn mpqemu_remote_msg_loop_co(void *data);
+
 #endif
diff --git a/hw/remote/message.c b/hw/remote/message.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2020, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL-v2, version 2 or later.
+ *
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/remote/machine.h"
+#include "io/channel.h"
+#include "hw/remote/mpqemu-link.h"
+#include "qapi/error.h"
+#include "sysemu/runstate.h"
+
+void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
+{
+    g_autofree RemoteCommDev *com = (RemoteCommDev *)data;
+    PCIDevice *pci_dev = NULL;
+    Error *local_err = NULL;
+
+    assert(com->ioc);
+
+    pci_dev = com->dev;
+    for (; !local_err;) {
+        MPQemuMsg msg = {0};
+
+        if (!mpqemu_msg_recv(&msg, com->ioc, &local_err)) {
+            break;
+        }
+
+        if (!mpqemu_msg_valid(&msg)) {
+            error_setg(&local_err, "Received invalid message from proxy"
+                                   "in remote process pid="FMT_pid"",
+                                   getpid());
+            break;
+        }
+
+        switch (msg.cmd) {
+        default:
+            error_setg(&local_err,
+                       "Unknown command (%d) received for device %s"
+                       " (pid="FMT_pid")",
+                       msg.cmd, DEVICE(pci_dev)->id, getpid());
+        }
+    }
+
+    if (local_err) {
+        error_report_err(local_err);
+        qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR);
+    } else {
+        qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
+    }
+}
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set()
 
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Associate the file descriptor for a PCIDevice in remote process with
DeviceState object.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: f405a2ed5d7518b87bea7c59cfdf334d67e5ee51.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS            |   1 +
 hw/remote/remote-obj.c | 203 +++++++++++++++++++++++++++++++++++++++++
 hw/remote/meson.build  |   1 +
 3 files changed, 205 insertions(+)
 create mode 100644 hw/remote/remote-obj.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: include/hw/remote/machine.h
 F: hw/remote/mpqemu-link.c
 F: include/hw/remote/mpqemu-link.h
 F: hw/remote/message.c
+F: hw/remote/remote-obj.c
 
 Build and test automation
 -------------------------
diff --git a/hw/remote/remote-obj.c b/hw/remote/remote-obj.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/remote-obj.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2020, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL-v2, version 2 or later.
+ *
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "qemu/error-report.h"
+#include "qemu/notify.h"
+#include "qom/object_interfaces.h"
+#include "hw/qdev-core.h"
+#include "io/channel.h"
+#include "hw/qdev-core.h"
+#include "hw/remote/machine.h"
+#include "io/channel-util.h"
+#include "qapi/error.h"
+#include "sysemu/sysemu.h"
+#include "hw/pci/pci.h"
+#include "qemu/sockets.h"
+#include "monitor/monitor.h"
+
+#define TYPE_REMOTE_OBJECT "x-remote-object"
+OBJECT_DECLARE_TYPE(RemoteObject, RemoteObjectClass, REMOTE_OBJECT)
+
+struct RemoteObjectClass {
+    ObjectClass parent_class;
+
+    unsigned int nr_devs;
+    unsigned int max_devs;
+};
+
+struct RemoteObject {
+    /* private */
+    Object parent;
+
+    Notifier machine_done;
+
+    int32_t fd;
+    char *devid;
+
+    QIOChannel *ioc;
+
+    DeviceState *dev;
+    DeviceListener listener;
+};
+
+static void remote_object_set_fd(Object *obj, const char *str, Error **errp)
+{
+    RemoteObject *o = REMOTE_OBJECT(obj);
+    int fd = -1;
+
+    fd = monitor_fd_param(monitor_cur(), str, errp);
+    if (fd == -1) {
+        error_prepend(errp, "Could not parse remote object fd %s:", str);
+        return;
+    }
+
+    if (!fd_is_socket(fd)) {
+        error_setg(errp, "File descriptor '%s' is not a socket", str);
+        close(fd);
+        return;
+    }
+
+    o->fd = fd;
+}
+
+static void remote_object_set_devid(Object *obj, const char *str, Error **errp)
+{
+    RemoteObject *o = REMOTE_OBJECT(obj);
+
+    g_free(o->devid);
+
+    o->devid = g_strdup(str);
+}
+
+static void remote_object_unrealize_listener(DeviceListener *listener,
+                                             DeviceState *dev)
+{
+    RemoteObject *o = container_of(listener, RemoteObject, listener);
+
+    if (o->dev == dev) {
+        object_unref(OBJECT(o));
+    }
+}
+
+static void remote_object_machine_done(Notifier *notifier, void *data)
+{
+    RemoteObject *o = container_of(notifier, RemoteObject, machine_done);
+    DeviceState *dev = NULL;
+    QIOChannel *ioc = NULL;
+    Coroutine *co = NULL;
+    RemoteCommDev *comdev = NULL;
+    Error *err = NULL;
+
+    dev = qdev_find_recursive(sysbus_get_default(), o->devid);
+    if (!dev || !object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
+        error_report("%s is not a PCI device", o->devid);
+        return;
+    }
+
+    ioc = qio_channel_new_fd(o->fd, &err);
+    if (!ioc) {
+        error_report_err(err);
+        return;
+    }
+    qio_channel_set_blocking(ioc, false, NULL);
+
+    o->dev = dev;
+
+    o->listener.unrealize = remote_object_unrealize_listener;
+    device_listener_register(&o->listener);
+
+    /* co-routine should free this. */
+    comdev = g_new0(RemoteCommDev, 1);
+    *comdev = (RemoteCommDev) {
+        .ioc = ioc,
+        .dev = PCI_DEVICE(dev),
+    };
+
+    co = qemu_coroutine_create(mpqemu_remote_msg_loop_co, comdev);
+    qemu_coroutine_enter(co);
+}
+
+static void remote_object_init(Object *obj)
+{
+    RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj);
+    RemoteObject *o = REMOTE_OBJECT(obj);
+
+    if (k->nr_devs >= k->max_devs) {
+        error_report("Reached maximum number of devices: %u", k->max_devs);
+        return;
+    }
+
+    o->ioc = NULL;
+    o->fd = -1;
+    o->devid = NULL;
+
+    k->nr_devs++;
+
+    o->machine_done.notify = remote_object_machine_done;
+    qemu_add_machine_init_done_notifier(&o->machine_done);
+}
+
+static void remote_object_finalize(Object *obj)
+{
+    RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj);
+    RemoteObject *o = REMOTE_OBJECT(obj);
+
+    device_listener_unregister(&o->listener);
+
+    if (o->ioc) {
+        qio_channel_shutdown(o->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+        qio_channel_close(o->ioc, NULL);
+    }
+
+    object_unref(OBJECT(o->ioc));
+
+    k->nr_devs--;
+    g_free(o->devid);
+}
+
+static void remote_object_class_init(ObjectClass *klass, void *data)
+{
+    RemoteObjectClass *k = REMOTE_OBJECT_CLASS(klass);
+
+    /*
+     * Limit number of supported devices to 1. This is done to avoid devices
+     * from one VM accessing the RAM of another VM. This is done until we
+     * start using separate address spaces for individual devices.
+     */
+    k->max_devs = 1;
+    k->nr_devs = 0;
+
+    object_class_property_add_str(klass, "fd", NULL, remote_object_set_fd);
+    object_class_property_add_str(klass, "devid", NULL,
+                                  remote_object_set_devid);
+}
+
+static const TypeInfo remote_object_info = {
+    .name = TYPE_REMOTE_OBJECT,
+    .parent = TYPE_OBJECT,
+    .instance_size = sizeof(RemoteObject),
+    .instance_init = remote_object_init,
+    .instance_finalize = remote_object_finalize,
+    .class_size = sizeof(RemoteObjectClass),
+    .class_init = remote_object_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_USER_CREATABLE },
+        { }
+    }
+};
+
+static void register_types(void)
+{
+    type_register_static(&remote_object_info);
+}
+
+type_init(register_types);
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set()
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

SyncSysMemMsg message format is defined. It is used to send
file descriptors of the RAM regions to remote device.
RAM on the remote device is configured with a set of file descriptors.
Old RAM regions are deleted and new regions, each with an fd, is
added to the RAM.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 7d2d1831d812e85f681e7a8ab99e032cf4704689.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                     |  2 +
 include/hw/remote/memory.h      | 19 ++++++++++
 include/hw/remote/mpqemu-link.h | 10 +++++
 hw/remote/memory.c              | 65 +++++++++++++++++++++++++++++++++
 hw/remote/mpqemu-link.c         | 11 ++++++
 hw/remote/meson.build           |  2 +
 6 files changed, 109 insertions(+)
 create mode 100644 include/hw/remote/memory.h
 create mode 100644 hw/remote/memory.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/mpqemu-link.c
 F: include/hw/remote/mpqemu-link.h
 F: hw/remote/message.c
 F: hw/remote/remote-obj.c
+F: include/hw/remote/memory.h
+F: hw/remote/memory.c
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/memory.h b/include/hw/remote/memory.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/memory.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Memory manager for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef REMOTE_MEMORY_H
+#define REMOTE_MEMORY_H
+
+#include "exec/hwaddr.h"
+#include "hw/remote/mpqemu-link.h"
+
+void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp);
+
+#endif
diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
 #include "qom/object.h"
 #include "qemu/thread.h"
 #include "io/channel.h"
+#include "exec/hwaddr.h"
 
 #define REMOTE_MAX_FDS 8
 
@@ -XXX,XX +XXX,XX @@
  *
  */
 typedef enum {
+    MPQEMU_CMD_SYNC_SYSMEM,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
+typedef struct {
+    hwaddr gpas[REMOTE_MAX_FDS];
+    uint64_t sizes[REMOTE_MAX_FDS];
+    off_t offsets[REMOTE_MAX_FDS];
+} SyncSysmemMsg;
+
 /**
  * MPQemuMsg:
  * @cmd: The remote command
@@ -XXX,XX +XXX,XX @@ typedef enum {
  * MPQemuMsg Format of the message sent to the remote device from QEMU.
  *
  */
+
 typedef struct {
     int cmd;
     size_t size;
 
     union {
         uint64_t u64;
+        SyncSysmemMsg sync_sysmem;
     } data;
 
     int fds[REMOTE_MAX_FDS];
diff --git a/hw/remote/memory.c b/hw/remote/memory.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/memory.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Memory manager for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/remote/memory.h"
+#include "exec/address-spaces.h"
+#include "exec/ram_addr.h"
+#include "qapi/error.h"
+
+static void remote_sysmem_reset(void)
+{
+    MemoryRegion *sysmem, *subregion, *next;
+
+    sysmem = get_system_memory();
+
+    QTAILQ_FOREACH_SAFE(subregion, &sysmem->subregions, subregions_link, next) {
+        if (subregion->ram) {
+            memory_region_del_subregion(sysmem, subregion);
+            object_unparent(OBJECT(subregion));
+        }
+    }
+}
+
+void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    SyncSysmemMsg *sysmem_info = &msg->data.sync_sysmem;
+    MemoryRegion *sysmem, *subregion;
+    static unsigned int suffix;
+    int region;
+
+    sysmem = get_system_memory();
+
+    remote_sysmem_reset();
+
+    for (region = 0; region < msg->num_fds; region++) {
+        g_autofree char *name;
+        subregion = g_new(MemoryRegion, 1);
+        name = g_strdup_printf("remote-mem-%u", suffix++);
+        memory_region_init_ram_from_fd(subregion, NULL,
+                                       name, sysmem_info->sizes[region],
+                                       true, msg->fds[region],
+                                       sysmem_info->offsets[region],
+                                       errp);
+
+        if (*errp) {
+            g_free(subregion);
+            remote_sysmem_reset();
+            return;
+        }
+
+        memory_region_add_subregion(sysmem, sysmem_info->gpas[region],
+                                    subregion);
+
+    }
+}
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
         }
     }
 
+     /* Verify message specific fields. */
+    switch (msg->cmd) {
+    case MPQEMU_CMD_SYNC_SYSMEM:
+        if (msg->num_fds == 0 || msg->size != sizeof(SyncSysmemMsg)) {
+            return false;
+        }
+        break;
+    default:
+        break;
+    }
+
     return true;
 }
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 
+specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
+
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Defines a PCI Device proxy object as a child of TYPE_PCI_DEVICE.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: b5186ebfedf8e557044d09a768846c59230ad3a7.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS               |  2 +
 include/hw/remote/proxy.h | 33 +++++++++++++
 hw/remote/proxy.c         | 99 +++++++++++++++++++++++++++++++++++++++
 hw/remote/meson.build     |  1 +
 4 files changed, 135 insertions(+)
 create mode 100644 include/hw/remote/proxy.h
 create mode 100644 hw/remote/proxy.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/message.c
 F: hw/remote/remote-obj.c
 F: include/hw/remote/memory.h
 F: hw/remote/memory.c
+F: hw/remote/proxy.c
+F: include/hw/remote/proxy.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef PROXY_H
+#define PROXY_H
+
+#include "hw/pci/pci.h"
+#include "io/channel.h"
+
+#define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
+OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
+
+struct PCIProxyDev {
+    PCIDevice parent_dev;
+    char *fd;
+
+    /*
+     * Mutex used to protect the QIOChannel fd from
+     * the concurrent access by the VCPUs since proxy
+     * blocks while awaiting for the replies from the
+     * process remote.
+     */
+    QemuMutex io_mutex;
+    QIOChannel *ioc;
+    Error *migration_blocker;
+};
+
+#endif /* PROXY_H */
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/remote/proxy.h"
+#include "hw/pci/pci.h"
+#include "qapi/error.h"
+#include "io/channel-util.h"
+#include "hw/qdev-properties.h"
+#include "monitor/monitor.h"
+#include "migration/blocker.h"
+#include "qemu/sockets.h"
+
+static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
+{
+    ERRP_GUARD();
+    PCIProxyDev *dev = PCI_PROXY_DEV(device);
+    int fd;
+
+    if (!dev->fd) {
+        error_setg(errp, "fd parameter not specified for %s",
+                   DEVICE(device)->id);
+        return;
+    }
+
+    fd = monitor_fd_param(monitor_cur(), dev->fd, errp);
+    if (fd == -1) {
+        error_prepend(errp, "proxy: unable to parse fd %s: ", dev->fd);
+        return;
+    }
+
+    if (!fd_is_socket(fd)) {
+        error_setg(errp, "proxy: fd %d is not a socket", fd);
+        close(fd);
+        return;
+    }
+
+    dev->ioc = qio_channel_new_fd(fd, errp);
+
+    error_setg(&dev->migration_blocker, "%s does not support migration",
+               TYPE_PCI_PROXY_DEV);
+    migrate_add_blocker(dev->migration_blocker, errp);
+
+    qemu_mutex_init(&dev->io_mutex);
+    qio_channel_set_blocking(dev->ioc, true, NULL);
+}
+
+static void pci_proxy_dev_exit(PCIDevice *pdev)
+{
+    PCIProxyDev *dev = PCI_PROXY_DEV(pdev);
+
+    if (dev->ioc) {
+        qio_channel_close(dev->ioc, NULL);
+    }
+
+    migrate_del_blocker(dev->migration_blocker);
+
+    error_free(dev->migration_blocker);
+}
+
+static Property proxy_properties[] = {
+    DEFINE_PROP_STRING("fd", PCIProxyDev, fd),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->realize = pci_proxy_dev_realize;
+    k->exit = pci_proxy_dev_exit;
+    device_class_set_props(dc, proxy_properties);
+}
+
+static const TypeInfo pci_proxy_dev_type_info = {
+    .name          = TYPE_PCI_PROXY_DEV,
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PCIProxyDev),
+    .class_init    = pci_proxy_dev_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { INTERFACE_CONVENTIONAL_PCI_DEVICE },
+        { },
+    },
+};
+
+static void pci_proxy_dev_register_types(void)
+{
+    type_register_static(&pci_proxy_dev_type_info);
+}
+
+type_init(pci_proxy_dev_register_types)
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
 
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: d54edb4176361eed86b903e8f27058363b6c83b3.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h |  4 ++++
 hw/remote/mpqemu-link.c         | 34 +++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
 #include "qemu/thread.h"
 #include "io/channel.h"
 #include "exec/hwaddr.h"
+#include "io/channel-socket.h"
+#include "hw/remote/proxy.h"
 
 #define REMOTE_MAX_FDS 8
 
@@ -XXX,XX +XXX,XX @@ typedef struct {
 bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
 bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
 
+uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
+                                         Error **errp);
 bool mpqemu_msg_valid(MPQemuMsg *msg);
 
 #endif
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ fail:
     return ret;
 }
 
+/*
+ * Send msg and wait for a reply with command code RET_MSG.
+ * Returns the message received of size u64 or UINT64_MAX
+ * on error.
+ * Called from VCPU thread in non-coroutine context.
+ * Used by the Proxy object to communicate to remote processes.
+ */
+uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
+                                         Error **errp)
+{
+    ERRP_GUARD();
+    MPQemuMsg msg_reply = {0};
+    uint64_t ret = UINT64_MAX;
+
+    assert(!qemu_in_coroutine());
+
+    QEMU_LOCK_GUARD(&pdev->io_mutex);
+    if (!mpqemu_msg_send(msg, pdev->ioc, errp)) {
+        return ret;
+    }
+
+    if (!mpqemu_msg_recv(&msg_reply, pdev->ioc, errp)) {
+        return ret;
+    }
+
+    if (!mpqemu_msg_valid(&msg_reply)) {
+        error_setg(errp, "ERROR: Invalid reply received for command %d",
+                         msg->cmd);
+        return ret;
+    }
+
+    return msg_reply.data.u64;
+}
+
 bool mpqemu_msg_valid(MPQemuMsg *msg)
 {
     if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) {
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

The Proxy Object sends the PCI config space accesses as messages
to the remote process over the communication channel

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: d3c94f4618813234655356c60e6f0d0362ff42d6.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h | 10 ++++++
 hw/remote/message.c             | 60 +++++++++++++++++++++++++++++++++
 hw/remote/mpqemu-link.c         |  8 ++++-
 hw/remote/proxy.c               | 55 ++++++++++++++++++++++++++++++
 4 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
  */
 typedef enum {
     MPQEMU_CMD_SYNC_SYSMEM,
+    MPQEMU_CMD_RET,
+    MPQEMU_CMD_PCI_CFGWRITE,
+    MPQEMU_CMD_PCI_CFGREAD,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
@@ -XXX,XX +XXX,XX @@ typedef struct {
     off_t offsets[REMOTE_MAX_FDS];
 } SyncSysmemMsg;
 
+typedef struct {
+    uint32_t addr;
+    uint32_t val;
+    int len;
+} PciConfDataMsg;
+
 /**
  * MPQemuMsg:
  * @cmd: The remote command
@@ -XXX,XX +XXX,XX @@ typedef struct {
 
     union {
         uint64_t u64;
+        PciConfDataMsg pci_conf_data;
         SyncSysmemMsg sync_sysmem;
     } data;
 
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/remote/mpqemu-link.h"
 #include "qapi/error.h"
 #include "sysemu/runstate.h"
+#include "hw/pci/pci.h"
+
+static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
+                                 MPQemuMsg *msg, Error **errp);
+static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
+                                MPQemuMsg *msg, Error **errp);
 
 void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
 {
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         }
 
         switch (msg.cmd) {
+        case MPQEMU_CMD_PCI_CFGWRITE:
+            process_config_write(com->ioc, pci_dev, &msg, &local_err);
+            break;
+        case MPQEMU_CMD_PCI_CFGREAD:
+            process_config_read(com->ioc, pci_dev, &msg, &local_err);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
     }
 }
+
+static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
+                                 MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data;
+    MPQemuMsg ret = { 0 };
+
+    if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) {
+        error_setg(errp, "Bad address for PCI config write, pid "FMT_pid".",
+                   getpid());
+        ret.data.u64 = UINT64_MAX;
+    } else {
+        pci_default_write_config(dev, conf->addr, conf->val, conf->len);
+    }
+
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
+
+static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
+                                MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data;
+    MPQemuMsg ret = { 0 };
+
+    if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) {
+        error_setg(errp, "Bad address for PCI config read, pid "FMT_pid".",
+                   getpid());
+        ret.data.u64 = UINT64_MAX;
+    } else {
+        ret.data.u64 = pci_default_read_config(dev, conf->addr, conf->len);
+    }
+
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
         return ret;
     }
 
-    if (!mpqemu_msg_valid(&msg_reply)) {
+    if (!mpqemu_msg_valid(&msg_reply) || msg_reply.cmd != MPQEMU_CMD_RET) {
         error_setg(errp, "ERROR: Invalid reply received for command %d",
                          msg->cmd);
         return ret;
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_PCI_CFGWRITE:
+    case MPQEMU_CMD_PCI_CFGREAD:
+        if (msg->size != sizeof(PciConfDataMsg)) {
+            return false;
+        }
+        break;
     default:
         break;
     }
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "monitor/monitor.h"
 #include "migration/blocker.h"
 #include "qemu/sockets.h"
+#include "hw/remote/mpqemu-link.h"
+#include "qemu/error-report.h"
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     error_free(dev->migration_blocker);
 }
 
+static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
+                           int len, unsigned int op)
+{
+    MPQemuMsg msg = { 0 };
+    uint64_t ret = -EINVAL;
+    Error *local_err = NULL;
+
+    msg.cmd = op;
+    msg.data.pci_conf_data.addr = addr;
+    msg.data.pci_conf_data.val = (op == MPQEMU_CMD_PCI_CFGWRITE) ? *val : 0;
+    msg.data.pci_conf_data.len = len;
+    msg.size = sizeof(PciConfDataMsg);
+
+    ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+
+    if (ret == UINT64_MAX) {
+        error_report("Failed to perform PCI config %s operation",
+                     (op == MPQEMU_CMD_PCI_CFGREAD) ? "READ" : "WRITE");
+    }
+
+    if (op == MPQEMU_CMD_PCI_CFGREAD) {
+        *val = (uint32_t)ret;
+    }
+}
+
+static uint32_t pci_proxy_read_config(PCIDevice *d, uint32_t addr, int len)
+{
+    uint32_t val;
+
+    config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGREAD);
+
+    return val;
+}
+
+static void pci_proxy_write_config(PCIDevice *d, uint32_t addr, uint32_t val,
+                                   int len)
+{
+    /*
+     * Some of the functions access the copy of remote device's PCI config
+     * space which is cached in the proxy device. Therefore, maintain
+     * it updated.
+     */
+    pci_default_write_config(d, addr, val, len);
+
+    config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGWRITE);
+}
+
 static Property proxy_properties[] = {
     DEFINE_PROP_STRING("fd", PCIProxyDev, fd),
     DEFINE_PROP_END_OF_LIST(),
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
 
     k->realize = pci_proxy_dev_realize;
     k->exit = pci_proxy_dev_exit;
+    k->config_read = pci_proxy_read_config;
+    k->config_write = pci_proxy_write_config;
+
     device_class_set_props(dc, proxy_properties);
 }
 
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Proxy device object implements handler for PCI BAR writes and reads.
The handler uses BAR_WRITE/BAR_READ message to communicate to the
remote process with the BAR address and value to be written/read.
The remote process implements handler for BAR_WRITE/BAR_READ
message.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: a8b76714a9688be5552c4c92d089bc9e8a4707ff.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h | 10 ++++
 include/hw/remote/proxy.h       |  9 ++++
 hw/remote/message.c             | 83 +++++++++++++++++++++++++++++++++
 hw/remote/mpqemu-link.c         |  6 +++
 hw/remote/proxy.c               | 60 ++++++++++++++++++++++++
 5 files changed, 168 insertions(+)

diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     MPQEMU_CMD_RET,
     MPQEMU_CMD_PCI_CFGWRITE,
     MPQEMU_CMD_PCI_CFGREAD,
+    MPQEMU_CMD_BAR_WRITE,
+    MPQEMU_CMD_BAR_READ,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
@@ -XXX,XX +XXX,XX @@ typedef struct {
     int len;
 } PciConfDataMsg;
 
+typedef struct {
+    hwaddr addr;
+    uint64_t val;
+    unsigned size;
+    bool memory;
+} BarAccessMsg;
+
 /**
  * MPQemuMsg:
  * @cmd: The remote command
@@ -XXX,XX +XXX,XX @@ typedef struct {
         uint64_t u64;
         PciConfDataMsg pci_conf_data;
         SyncSysmemMsg sync_sysmem;
+        BarAccessMsg bar_access;
     } data;
 
     int fds[REMOTE_MAX_FDS];
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/proxy.h
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
 
+typedef struct ProxyMemoryRegion {
+    PCIProxyDev *dev;
+    MemoryRegion mr;
+    bool memory;
+    bool present;
+    uint8_t type;
+} ProxyMemoryRegion;
+
 struct PCIProxyDev {
     PCIDevice parent_dev;
     char *fd;
@@ -XXX,XX +XXX,XX @@ struct PCIProxyDev {
     QemuMutex io_mutex;
     QIOChannel *ioc;
     Error *migration_blocker;
+    ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
 #endif /* PROXY_H */
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "qapi/error.h"
 #include "sysemu/runstate.h"
 #include "hw/pci/pci.h"
+#include "exec/memattrs.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
 static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
                                 MPQemuMsg *msg, Error **errp);
+static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp);
+static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp);
 
 void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
 {
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_PCI_CFGREAD:
             process_config_read(com->ioc, pci_dev, &msg, &local_err);
             break;
+        case MPQEMU_CMD_BAR_WRITE:
+            process_bar_write(com->ioc, &msg, &local_err);
+            break;
+        case MPQEMU_CMD_BAR_READ:
+            process_bar_read(com->ioc, &msg, &local_err);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
@@ -XXX,XX +XXX,XX @@ static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
                       getpid());
     }
 }
+
+static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    BarAccessMsg *bar_access = &msg->data.bar_access;
+    AddressSpace *as =
+        bar_access->memory ? &address_space_memory : &address_space_io;
+    MPQemuMsg ret = { 0 };
+    MemTxResult res;
+    uint64_t val;
+
+    if (!is_power_of_2(bar_access->size) ||
+       (bar_access->size > sizeof(uint64_t))) {
+        ret.data.u64 = UINT64_MAX;
+        goto fail;
+    }
+
+    val = cpu_to_le64(bar_access->val);
+
+    res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED,
+                           (void *)&val, bar_access->size, true);
+
+    if (res != MEMTX_OK) {
+        error_setg(errp, "Bad address %"PRIx64" for mem write, pid "FMT_pid".",
+                   bar_access->addr, getpid());
+        ret.data.u64 = -1;
+    }
+
+fail:
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
+
+static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    BarAccessMsg *bar_access = &msg->data.bar_access;
+    MPQemuMsg ret = { 0 };
+    AddressSpace *as;
+    MemTxResult res;
+    uint64_t val = 0;
+
+    as = bar_access->memory ? &address_space_memory : &address_space_io;
+
+    if (!is_power_of_2(bar_access->size) ||
+       (bar_access->size > sizeof(uint64_t))) {
+        val = UINT64_MAX;
+        goto fail;
+    }
+
+    res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED,
+                           (void *)&val, bar_access->size, false);
+
+    if (res != MEMTX_OK) {
+        error_setg(errp, "Bad address %"PRIx64" for mem read, pid "FMT_pid".",
+                   bar_access->addr, getpid());
+        val = UINT64_MAX;
+    }
+
+fail:
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.data.u64 = le64_to_cpu(val);
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_BAR_WRITE:
+    case MPQEMU_CMD_BAR_READ:
+        if ((msg->size != sizeof(BarAccessMsg)) || (msg->num_fds != 0)) {
+            return false;
+        }
+        break;
     default:
         break;
     }
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_register_types(void)
 }
 
 type_init(pci_proxy_dev_register_types)
+
+static void send_bar_access_msg(PCIProxyDev *pdev, MemoryRegion *mr,
+                                bool write, hwaddr addr, uint64_t *val,
+                                unsigned size, bool memory)
+{
+    MPQemuMsg msg = { 0 };
+    long ret = -EINVAL;
+    Error *local_err = NULL;
+
+    msg.size = sizeof(BarAccessMsg);
+    msg.data.bar_access.addr = mr->addr + addr;
+    msg.data.bar_access.size = size;
+    msg.data.bar_access.memory = memory;
+
+    if (write) {
+        msg.cmd = MPQEMU_CMD_BAR_WRITE;
+        msg.data.bar_access.val = *val;
+    } else {
+        msg.cmd = MPQEMU_CMD_BAR_READ;
+    }
+
+    ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+
+    if (!write) {
+        *val = ret;
+    }
+}
+
+static void proxy_bar_write(void *opaque, hwaddr addr, uint64_t val,
+                            unsigned size)
+{
+    ProxyMemoryRegion *pmr = opaque;
+
+    send_bar_access_msg(pmr->dev, &pmr->mr, true, addr, &val, size,
+                        pmr->memory);
+}
+
+static uint64_t proxy_bar_read(void *opaque, hwaddr addr, unsigned size)
+{
+    ProxyMemoryRegion *pmr = opaque;
+    uint64_t val;
+
+    send_bar_access_msg(pmr->dev, &pmr->mr, false, addr, &val, size,
+                        pmr->memory);
+
+    return val;
+}
+
+const MemoryRegionOps proxy_mr_ops = {
+    .read = proxy_bar_read,
+    .write = proxy_bar_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+};
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Add ProxyMemoryListener object which is used to keep the view of the RAM
in sync between QEMU and remote process.
A MemoryListener is registered for system-memory AddressSpace. The
listener sends SYNC_SYSMEM message to the remote process when memory
listener commits the changes to memory, the remote process receives
the message and processes it in the handler for SYNC_SYSMEM message.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 04fe4e6a9ca90d4f11ab6f59be7652f5b086a071.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                               |   2 +
 include/hw/remote/proxy-memory-listener.h |  28 +++
 include/hw/remote/proxy.h                 |   2 +
 hw/remote/message.c                       |   4 +
 hw/remote/proxy-memory-listener.c         | 227 ++++++++++++++++++++++
 hw/remote/proxy.c                         |   6 +
 hw/remote/meson.build                     |   1 +
 7 files changed, 270 insertions(+)
 create mode 100644 include/hw/remote/proxy-memory-listener.h
 create mode 100644 hw/remote/proxy-memory-listener.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: include/hw/remote/memory.h
 F: hw/remote/memory.c
 F: hw/remote/proxy.c
 F: include/hw/remote/proxy.h
+F: hw/remote/proxy-memory-listener.c
+F: include/hw/remote/proxy-memory-listener.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/proxy-memory-listener.h b/include/hw/remote/proxy-memory-listener.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/proxy-memory-listener.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef PROXY_MEMORY_LISTENER_H
+#define PROXY_MEMORY_LISTENER_H
+
+#include "exec/memory.h"
+#include "io/channel.h"
+
+typedef struct ProxyMemoryListener {
+    MemoryListener listener;
+
+    int n_mr_sections;
+    MemoryRegionSection *mr_sections;
+
+    QIOChannel *ioc;
+} ProxyMemoryListener;
+
+void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener,
+                                     QIOChannel *ioc);
+void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener);
+
+#endif
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/proxy.h
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
 
 #include "hw/pci/pci.h"
 #include "io/channel.h"
+#include "hw/remote/proxy-memory-listener.h"
 
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
@@ -XXX,XX +XXX,XX @@ struct PCIProxyDev {
     QemuMutex io_mutex;
     QIOChannel *ioc;
     Error *migration_blocker;
+    ProxyMemoryListener proxy_listener;
     ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/runstate.h"
 #include "hw/pci/pci.h"
 #include "exec/memattrs.h"
+#include "hw/remote/memory.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_BAR_READ:
             process_bar_read(com->ioc, &msg, &local_err);
             break;
+        case MPQEMU_CMD_SYNC_SYSMEM:
+            remote_sysmem_reconfig(&msg, &local_err);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/proxy-memory-listener.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "qemu/compiler.h"
+#include "qemu/int128.h"
+#include "qemu/range.h"
+#include "exec/memory.h"
+#include "exec/cpu-common.h"
+#include "cpu.h"
+#include "exec/ram_addr.h"
+#include "exec/address-spaces.h"
+#include "qapi/error.h"
+#include "hw/remote/mpqemu-link.h"
+#include "hw/remote/proxy-memory-listener.h"
+
+/*
+ * TODO: get_fd_from_hostaddr(), proxy_mrs_can_merge() and
+ * proxy_memory_listener_commit() defined below perform tasks similar to the
+ * functions defined in vhost-user.c. These functions are good candidates
+ * for refactoring.
+ *
+ */
+
+static void proxy_memory_listener_reset(MemoryListener *listener)
+{
+    ProxyMemoryListener *proxy_listener = container_of(listener,
+                                                       ProxyMemoryListener,
+                                                       listener);
+    int mrs;
+
+    for (mrs = 0; mrs < proxy_listener->n_mr_sections; mrs++) {
+        memory_region_unref(proxy_listener->mr_sections[mrs].mr);
+    }
+
+    g_free(proxy_listener->mr_sections);
+    proxy_listener->mr_sections = NULL;
+    proxy_listener->n_mr_sections = 0;
+}
+
+static int get_fd_from_hostaddr(uint64_t host, ram_addr_t *offset)
+{
+    MemoryRegion *mr;
+    ram_addr_t off;
+
+    /**
+     * Assumes that the host address is a valid address as it's
+     * coming from the MemoryListener system. In the case host
+     * address is not valid, the following call would return
+     * the default subregion of "system_memory" region, and
+     * not NULL. So it's not possible to check for NULL here.
+     */
+    mr = memory_region_from_host((void *)(uintptr_t)host, &off);
+
+    if (offset) {
+        *offset = off;
+    }
+
+    return memory_region_get_fd(mr);
+}
+
+static bool proxy_mrs_can_merge(uint64_t host, uint64_t prev_host, size_t size)
+{
+    if (((prev_host + size) != host)) {
+        return false;
+    }
+
+    if (get_fd_from_hostaddr(host, NULL) !=
+            get_fd_from_hostaddr(prev_host, NULL)) {
+        return false;
+    }
+
+    return true;
+}
+
+static bool try_merge(ProxyMemoryListener *proxy_listener,
+                      MemoryRegionSection *section)
+{
+    uint64_t mrs_size, mrs_gpa, mrs_page;
+    MemoryRegionSection *prev_sec;
+    bool merged = false;
+    uintptr_t mrs_host;
+    RAMBlock *mrs_rb;
+
+    if (!proxy_listener->n_mr_sections) {
+        return false;
+    }
+
+    mrs_rb = section->mr->ram_block;
+    mrs_page = (uint64_t)qemu_ram_pagesize(mrs_rb);
+    mrs_size = int128_get64(section->size);
+    mrs_gpa = section->offset_within_address_space;
+    mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
+               section->offset_within_region;
+
+    if (get_fd_from_hostaddr(mrs_host, NULL) < 0) {
+        return true;
+    }
+
+    mrs_host = mrs_host & ~(mrs_page - 1);
+    mrs_gpa = mrs_gpa & ~(mrs_page - 1);
+    mrs_size = ROUND_UP(mrs_size, mrs_page);
+
+    prev_sec = proxy_listener->mr_sections +
+               (proxy_listener->n_mr_sections - 1);
+    uint64_t prev_gpa_start = prev_sec->offset_within_address_space;
+    uint64_t prev_size = int128_get64(prev_sec->size);
+    uint64_t prev_gpa_end   = range_get_last(prev_gpa_start, prev_size);
+    uint64_t prev_host_start =
+        (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) +
+        prev_sec->offset_within_region;
+    uint64_t prev_host_end = range_get_last(prev_host_start, prev_size);
+
+    if (mrs_gpa <= (prev_gpa_end + 1)) {
+        g_assert(mrs_gpa > prev_gpa_start);
+
+        if ((section->mr == prev_sec->mr) &&
+            proxy_mrs_can_merge(mrs_host, prev_host_start,
+                                (mrs_gpa - prev_gpa_start))) {
+            uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size);
+            merged = true;
+            prev_sec->offset_within_address_space =
+                MIN(prev_gpa_start, mrs_gpa);
+            prev_sec->offset_within_region =
+                MIN(prev_host_start, mrs_host) -
+                (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr);
+            prev_sec->size = int128_make64(max_end - MIN(prev_host_start,
+                                                         mrs_host));
+        }
+    }
+
+    return merged;
+}
+
+static void proxy_memory_listener_region_addnop(MemoryListener *listener,
+                                                MemoryRegionSection *section)
+{
+    ProxyMemoryListener *proxy_listener = container_of(listener,
+                                                       ProxyMemoryListener,
+                                                       listener);
+
+    if (!memory_region_is_ram(section->mr) ||
+            memory_region_is_rom(section->mr)) {
+        return;
+    }
+
+    if (try_merge(proxy_listener, section)) {
+        return;
+    }
+
+    ++proxy_listener->n_mr_sections;
+    proxy_listener->mr_sections = g_renew(MemoryRegionSection,
+                                          proxy_listener->mr_sections,
+                                          proxy_listener->n_mr_sections);
+    proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1] = *section;
+    proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1].fv = NULL;
+    memory_region_ref(section->mr);
+}
+
+static void proxy_memory_listener_commit(MemoryListener *listener)
+{
+    ProxyMemoryListener *proxy_listener = container_of(listener,
+                                                       ProxyMemoryListener,
+                                                       listener);
+    MPQemuMsg msg;
+    MemoryRegionSection *section;
+    ram_addr_t offset;
+    uintptr_t host_addr;
+    int region;
+    Error *local_err = NULL;
+
+    memset(&msg, 0, sizeof(MPQemuMsg));
+
+    msg.cmd = MPQEMU_CMD_SYNC_SYSMEM;
+    msg.num_fds = proxy_listener->n_mr_sections;
+    msg.size = sizeof(SyncSysmemMsg);
+    if (msg.num_fds > REMOTE_MAX_FDS) {
+        error_report("Number of fds is more than %d", REMOTE_MAX_FDS);
+        return;
+    }
+
+    for (region = 0; region < proxy_listener->n_mr_sections; region++) {
+        section = &proxy_listener->mr_sections[region];
+        msg.data.sync_sysmem.gpas[region] =
+            section->offset_within_address_space;
+        msg.data.sync_sysmem.sizes[region] = int128_get64(section->size);
+        host_addr = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
+                    section->offset_within_region;
+        msg.fds[region] = get_fd_from_hostaddr(host_addr, &offset);
+        msg.data.sync_sysmem.offsets[region] = offset;
+    }
+    if (!mpqemu_msg_send(&msg, proxy_listener->ioc, &local_err)) {
+        error_report_err(local_err);
+    }
+}
+
+void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener)
+{
+    memory_listener_unregister(&proxy_listener->listener);
+
+    proxy_memory_listener_reset(&proxy_listener->listener);
+}
+
+void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener,
+                                     QIOChannel *ioc)
+{
+    proxy_listener->n_mr_sections = 0;
+    proxy_listener->mr_sections = NULL;
+
+    proxy_listener->ioc = ioc;
+
+    proxy_listener->listener.begin = proxy_memory_listener_reset;
+    proxy_listener->listener.commit = proxy_memory_listener_commit;
+    proxy_listener->listener.region_add = proxy_memory_listener_region_addnop;
+    proxy_listener->listener.region_nop = proxy_memory_listener_region_addnop;
+    proxy_listener->listener.priority = 10;
+
+    memory_listener_register(&proxy_listener->listener,
+                             &address_space_memory);
+}
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/sockets.h"
 #include "hw/remote/mpqemu-link.h"
 #include "qemu/error-report.h"
+#include "hw/remote/proxy-memory-listener.h"
+#include "qom/object.h"
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 
     qemu_mutex_init(&dev->io_mutex);
     qio_channel_set_blocking(dev->ioc, true, NULL);
+
+    proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     migrate_del_blocker(dev->migration_blocker);
 
     error_free(dev->migration_blocker);
+
+    proxy_memory_listener_deconfigure(&dev->proxy_listener);
 }
 
 static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
+specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

IOHUB object is added to manage PCI IRQs. It uses KVM_IRQFD
ioctl to create irqfd to injecting PCI interrupts to the guest.
IOHUB object forwards the irqfd to the remote process. Remote process
uses this fd to directly send interrupts to the guest, bypassing QEMU.

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 51d5c3d54e28a68b002e3875c59599c9f5a424a1.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                     |   2 +
 include/hw/pci/pci_ids.h        |   3 +
 include/hw/remote/iohub.h       |  42 +++++++++++
 include/hw/remote/machine.h     |   2 +
 include/hw/remote/mpqemu-link.h |   1 +
 include/hw/remote/proxy.h       |   4 ++
 hw/remote/iohub.c               | 119 ++++++++++++++++++++++++++++++++
 hw/remote/machine.c             |  10 +++
 hw/remote/message.c             |   4 ++
 hw/remote/mpqemu-link.c         |   5 ++
 hw/remote/proxy.c               |  56 +++++++++++++++
 hw/remote/meson.build           |   1 +
 12 files changed, 249 insertions(+)
 create mode 100644 include/hw/remote/iohub.h
 create mode 100644 hw/remote/iohub.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/proxy.c
 F: include/hw/remote/proxy.h
 F: hw/remote/proxy-memory-listener.c
 F: include/hw/remote/proxy-memory-listener.h
+F: hw/remote/iohub.c
+F: include/hw/remote/iohub.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/pci/pci_ids.h
+++ b/include/hw/pci/pci_ids.h
@@ -XXX,XX +XXX,XX @@
 #define PCI_DEVICE_ID_SUN_SIMBA          0x5000
 #define PCI_DEVICE_ID_SUN_SABRE          0xa000
 
+#define PCI_VENDOR_ID_ORACLE             0x108e
+#define PCI_DEVICE_ID_REMOTE_IOHUB       0xb000
+
 #define PCI_VENDOR_ID_CMD                0x1095
 #define PCI_DEVICE_ID_CMD_646            0x0646
 
diff --git a/include/hw/remote/iohub.h b/include/hw/remote/iohub.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/iohub.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * IO Hub for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef REMOTE_IOHUB_H
+#define REMOTE_IOHUB_H
+
+#include "hw/pci/pci.h"
+#include "qemu/event_notifier.h"
+#include "qemu/thread-posix.h"
+#include "hw/remote/mpqemu-link.h"
+
+#define REMOTE_IOHUB_NB_PIRQS    PCI_DEVFN_MAX
+
+typedef struct ResampleToken {
+    void *iohub;
+    int pirq;
+} ResampleToken;
+
+typedef struct RemoteIOHubState {
+    PCIDevice d;
+    EventNotifier irqfds[REMOTE_IOHUB_NB_PIRQS];
+    EventNotifier resamplefds[REMOTE_IOHUB_NB_PIRQS];
+    unsigned int irq_level[REMOTE_IOHUB_NB_PIRQS];
+    ResampleToken token[REMOTE_IOHUB_NB_PIRQS];
+    QemuMutex irq_level_lock[REMOTE_IOHUB_NB_PIRQS];
+} RemoteIOHubState;
+
+int remote_iohub_map_irq(PCIDevice *pci_dev, int intx);
+void remote_iohub_set_irq(void *opaque, int pirq, int level);
+void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg);
+
+void remote_iohub_init(RemoteIOHubState *iohub);
+void remote_iohub_finalize(RemoteIOHubState *iohub);
+
+#endif
diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/machine.h
+++ b/include/hw/remote/machine.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/boards.h"
 #include "hw/pci-host/remote.h"
 #include "io/channel.h"
+#include "hw/remote/iohub.h"
 
 struct RemoteMachineState {
     MachineState parent_obj;
 
     RemotePCIHost *host;
+    RemoteIOHubState iohub;
 };
 
 /* Used to pass to co-routine device and ioc. */
diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     MPQEMU_CMD_PCI_CFGREAD,
     MPQEMU_CMD_BAR_WRITE,
     MPQEMU_CMD_BAR_READ,
+    MPQEMU_CMD_SET_IRQFD,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/proxy.h
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci/pci.h"
 #include "io/channel.h"
 #include "hw/remote/proxy-memory-listener.h"
+#include "qemu/event_notifier.h"
 
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
@@ -XXX,XX +XXX,XX @@ struct PCIProxyDev {
     QIOChannel *ioc;
     Error *migration_blocker;
     ProxyMemoryListener proxy_listener;
+    int virq;
+    EventNotifier intr;
+    EventNotifier resample;
     ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
diff --git a/hw/remote/iohub.c b/hw/remote/iohub.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/iohub.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Remote IO Hub
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_ids.h"
+#include "hw/pci/pci_bus.h"
+#include "qemu/thread.h"
+#include "hw/boards.h"
+#include "hw/remote/machine.h"
+#include "hw/remote/iohub.h"
+#include "qemu/main-loop.h"
+
+void remote_iohub_init(RemoteIOHubState *iohub)
+{
+    int pirq;
+
+    memset(&iohub->irqfds, 0, sizeof(iohub->irqfds));
+    memset(&iohub->resamplefds, 0, sizeof(iohub->resamplefds));
+
+    for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) {
+        qemu_mutex_init(&iohub->irq_level_lock[pirq]);
+        iohub->irq_level[pirq] = 0;
+        event_notifier_init_fd(&iohub->irqfds[pirq], -1);
+        event_notifier_init_fd(&iohub->resamplefds[pirq], -1);
+    }
+}
+
+void remote_iohub_finalize(RemoteIOHubState *iohub)
+{
+    int pirq;
+
+    for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) {
+        qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]),
+                            NULL, NULL, NULL);
+        event_notifier_cleanup(&iohub->irqfds[pirq]);
+        event_notifier_cleanup(&iohub->resamplefds[pirq]);
+        qemu_mutex_destroy(&iohub->irq_level_lock[pirq]);
+    }
+}
+
+int remote_iohub_map_irq(PCIDevice *pci_dev, int intx)
+{
+    return pci_dev->devfn;
+}
+
+void remote_iohub_set_irq(void *opaque, int pirq, int level)
+{
+    RemoteIOHubState *iohub = opaque;
+
+    assert(pirq >= 0);
+    assert(pirq < PCI_DEVFN_MAX);
+
+    QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]);
+
+    if (level) {
+        if (++iohub->irq_level[pirq] == 1) {
+            event_notifier_set(&iohub->irqfds[pirq]);
+        }
+    } else if (iohub->irq_level[pirq] > 0) {
+        iohub->irq_level[pirq]--;
+    }
+}
+
+static void intr_resample_handler(void *opaque)
+{
+    ResampleToken *token = opaque;
+    RemoteIOHubState *iohub = token->iohub;
+    int pirq, s;
+
+    pirq = token->pirq;
+
+    s = event_notifier_test_and_clear(&iohub->resamplefds[pirq]);
+
+    assert(s >= 0);
+
+    QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]);
+
+    if (iohub->irq_level[pirq]) {
+        event_notifier_set(&iohub->irqfds[pirq]);
+    }
+}
+
+void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg)
+{
+    RemoteMachineState *machine = REMOTE_MACHINE(current_machine);
+    RemoteIOHubState *iohub = &machine->iohub;
+    int pirq, intx;
+
+    intx = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+
+    pirq = remote_iohub_map_irq(pci_dev, intx);
+
+    if (event_notifier_get_fd(&iohub->irqfds[pirq]) != -1) {
+        qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]),
+                            NULL, NULL, NULL);
+        event_notifier_cleanup(&iohub->irqfds[pirq]);
+        event_notifier_cleanup(&iohub->resamplefds[pirq]);
+        memset(&iohub->token[pirq], 0, sizeof(ResampleToken));
+    }
+
+    event_notifier_init_fd(&iohub->irqfds[pirq], msg->fds[0]);
+    event_notifier_init_fd(&iohub->resamplefds[pirq], msg->fds[1]);
+
+    iohub->token[pirq].iohub = iohub;
+    iohub->token[pirq].pirq = pirq;
+
+    qemu_set_fd_handler(msg->fds[1], intr_resample_handler, NULL,
+                        &iohub->token[pirq]);
+}
diff --git a/hw/remote/machine.c b/hw/remote/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/machine.c
+++ b/hw/remote/machine.c
@@ -XXX,XX +XXX,XX @@
 #include "exec/address-spaces.h"
 #include "exec/memory.h"
 #include "qapi/error.h"
+#include "hw/pci/pci_host.h"
+#include "hw/remote/iohub.h"
 
 static void remote_machine_init(MachineState *machine)
 {
     MemoryRegion *system_memory, *system_io, *pci_memory;
     RemoteMachineState *s = REMOTE_MACHINE(machine);
     RemotePCIHost *rem_host;
+    PCIHostState *pci_host;
 
     system_memory = get_system_memory();
     system_io = get_system_io();
@@ -XXX,XX +XXX,XX @@ static void remote_machine_init(MachineState *machine)
     memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1);
 
     qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal);
+
+    pci_host = PCI_HOST_BRIDGE(rem_host);
+
+    remote_iohub_init(&s->iohub);
+
+    pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq,
+                 &s->iohub, REMOTE_IOHUB_NB_PIRQS);
 }
 
 static void remote_machine_class_init(ObjectClass *oc, void *data)
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci/pci.h"
 #include "exec/memattrs.h"
 #include "hw/remote/memory.h"
+#include "hw/remote/iohub.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_SYNC_SYSMEM:
             remote_sysmem_reconfig(&msg, &local_err);
             break;
+        case MPQEMU_CMD_SET_IRQFD:
+            process_set_irqfd_msg(pci_dev, &msg);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_SET_IRQFD:
+        if (msg->size || (msg->num_fds != 2)) {
+            return false;
+        }
+        break;
     default:
         break;
     }
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/error-report.h"
 #include "hw/remote/proxy-memory-listener.h"
 #include "qom/object.h"
+#include "qemu/event_notifier.h"
+#include "sysemu/kvm.h"
+#include "util/event_notifier-posix.c"
+
+static void proxy_intx_update(PCIDevice *pci_dev)
+{
+    PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev);
+    PCIINTxRoute route;
+    int pin = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+
+    if (dev->virq != -1) {
+        kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &dev->intr, dev->virq);
+        dev->virq = -1;
+    }
+
+    route = pci_device_route_intx_to_irq(pci_dev, pin);
+
+    dev->virq = route.irq;
+
+    if (dev->virq != -1) {
+        kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &dev->intr,
+                                           &dev->resample, dev->virq);
+    }
+}
+
+static void setup_irqfd(PCIProxyDev *dev)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    MPQemuMsg msg;
+    Error *local_err = NULL;
+
+    event_notifier_init(&dev->intr, 0);
+    event_notifier_init(&dev->resample, 0);
+
+    memset(&msg, 0, sizeof(MPQemuMsg));
+    msg.cmd = MPQEMU_CMD_SET_IRQFD;
+    msg.num_fds = 2;
+    msg.fds[0] = event_notifier_get_fd(&dev->intr);
+    msg.fds[1] = event_notifier_get_fd(&dev->resample);
+    msg.size = 0;
+
+    if (!mpqemu_msg_send(&msg, dev->ioc, &local_err)) {
+        error_report_err(local_err);
+    }
+
+    dev->virq = -1;
+
+    proxy_intx_update(pci_dev);
+
+    pci_device_set_intx_routing_notifier(pci_dev, proxy_intx_update);
+}
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
     qio_channel_set_blocking(dev->ioc, true, NULL);
 
     proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
+
+    setup_irqfd(dev);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     error_free(dev->migration_blocker);
 
     proxy_memory_listener_deconfigure(&dev->proxy_listener);
+
+    event_notifier_cleanup(&dev->intr);
+    event_notifier_cleanup(&dev->resample);
 }
 
 static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c'))
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Retrieve PCI configuration info about the remote device and
configure the Proxy PCI object based on the returned information

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 85ee367bbb993aa23699b44cfedd83b4ea6d5221.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/remote/proxy.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 84 insertions(+)

diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/kvm.h"
 #include "util/event_notifier-posix.c"
 
+static void probe_pci_info(PCIDevice *dev, Error **errp);
+
 static void proxy_intx_update(PCIDevice *pci_dev)
 {
     PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev);
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
     ERRP_GUARD();
     PCIProxyDev *dev = PCI_PROXY_DEV(device);
+    uint8_t *pci_conf = device->config;
     int fd;
 
     if (!dev->fd) {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
     qemu_mutex_init(&dev->io_mutex);
     qio_channel_set_blocking(dev->ioc, true, NULL);
 
+    pci_conf[PCI_LATENCY_TIMER] = 0xff;
+    pci_conf[PCI_INTERRUPT_PIN] = 0x01;
+
     proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
 
     setup_irqfd(dev);
+
+    probe_pci_info(PCI_DEVICE(dev), errp);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -XXX,XX +XXX,XX @@ const MemoryRegionOps proxy_mr_ops = {
         .max_access_size = 8,
     },
 };
+
+static void probe_pci_info(PCIDevice *dev, Error **errp)
+{
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
+    uint32_t orig_val, new_val, base_class, val;
+    PCIProxyDev *pdev = PCI_PROXY_DEV(dev);
+    DeviceClass *dc = DEVICE_CLASS(pc);
+    uint8_t type;
+    int i, size;
+
+    config_op_send(pdev, PCI_VENDOR_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->vendor_id = (uint16_t)val;
+
+    config_op_send(pdev, PCI_DEVICE_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->device_id = (uint16_t)val;
+
+    config_op_send(pdev, PCI_CLASS_DEVICE, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->class_id = (uint16_t)val;
+
+    config_op_send(pdev, PCI_SUBSYSTEM_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->subsystem_id = (uint16_t)val;
+
+    base_class = pc->class_id >> 4;
+    switch (base_class) {
+    case PCI_BASE_CLASS_BRIDGE:
+        set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+        break;
+    case PCI_BASE_CLASS_STORAGE:
+        set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+        break;
+    case PCI_BASE_CLASS_NETWORK:
+        set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
+        break;
+    case PCI_BASE_CLASS_INPUT:
+        set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
+        break;
+    case PCI_BASE_CLASS_DISPLAY:
+        set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
+        break;
+    case PCI_BASE_CLASS_PROCESSOR:
+        set_bit(DEVICE_CATEGORY_CPU, dc->categories);
+        break;
+    default:
+        set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+        break;
+    }
+
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4,
+                       MPQEMU_CMD_PCI_CFGREAD);
+        new_val = 0xffffffff;
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4,
+                       MPQEMU_CMD_PCI_CFGWRITE);
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4,
+                       MPQEMU_CMD_PCI_CFGREAD);
+        size = (~(new_val & 0xFFFFFFF0)) + 1;
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4,
+                       MPQEMU_CMD_PCI_CFGWRITE);
+        type = (new_val & 0x1) ?
+                   PCI_BASE_ADDRESS_SPACE_IO : PCI_BASE_ADDRESS_SPACE_MEMORY;
+
+        if (size) {
+            g_autofree char *name;
+            pdev->region[i].dev = pdev;
+            pdev->region[i].present = true;
+            if (type == PCI_BASE_ADDRESS_SPACE_MEMORY) {
+                pdev->region[i].memory = true;
+            }
+            name = g_strdup_printf("bar-region-%d", i);
+            memory_region_init_io(&pdev->region[i].mr, OBJECT(pdev),
+                                  &proxy_mr_ops, &pdev->region[i],
+                                  name, size);
+            pci_register_bar(dev, i, type, &pdev->region[i].mr);
+        }
+    }
+}
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Perform device reset in the remote process when QEMU performs
device reset. This is required to reset the internal state
(like registers, etc...) of emulated devices

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 7cb220a51f565dc0817bd76e2f540e89c2d2b850.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h |  1 +
 hw/remote/message.c             | 22 ++++++++++++++++++++++
 hw/remote/proxy.c               | 19 +++++++++++++++++++
 3 files changed, 42 insertions(+)

From: "Denis V. Lunev" <den@openvz.org>

Original specification says that l1 table size if 64 * l1_size, which
is obviously wrong. The size of the l1 entry is 64 _bits_, not bytes.
Thus 64 is to be replaces with 8 as specification says about bytes.

There is also minor tweak, field name is renamed from l1 to l1_table,
which matches with the later text.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-id: 20210128171313.2210947-1-den@openvz.org
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

[Replace the original commit message "docs: fix mistake in dirty bitmap
feature description" as suggested by Eric Blake.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 docs/interop/parallels.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/interop/parallels.txt b/docs/interop/parallels.txt
index XXXXXXX..XXXXXXX 100644
--- a/docs/interop/parallels.txt
+++ b/docs/interop/parallels.txt
@@ -XXX,XX +XXX,XX @@ of its data area are:
   28 - 31:    l1_size
               The number of entries in the L1 table of the bitmap.
 
-  variable:   l1 (64 * l1_size bytes)
+  variable:   l1_table (8 * l1_size bytes)
               L1 offset table (in bytes)
 
 A dirty bitmap is stored using a one-level structure for the mapping to host
-- 
2.29.2