The following changes since commit 1be5a765c08cee3a9587c8a8d3fc2ea247b13f9c:

Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2022-04-19 18:22:16 -0700)

are available in the Git repository at:

https://gitlab.com/hreitz/qemu.git tags/pull-block-2022-04-20

for you to fetch changes up to 0423f75351ab83b844a31349218b0eadd830e07a:

qcow2: Add errp to rebuild_refcount_structure() (2022-04-20 12:09:17 +0200)

Thomas Huth (2):

tests/qemu-iotests/meson.build: Improve the indentation

tests/qemu-iotests: Move the bash and sanitizer checks to meson.build

block/qcow2-refcount.c | 353 +++++++++++++++++++++++----------

tests/check-block.sh | 26 ---

tests/qemu-iotests/065 | 24 ++-

tests/qemu-iotests/108 | 259 +++++++++++++++++++++++-

tests/qemu-iotests/108.out | 81 ++++++++

tests/qemu-iotests/303 | 4 +-

tests/qemu-iotests/iotests.py | 20 ++

tests/qemu-iotests/meson.build | 73 ++++---

8 files changed, 673 insertions(+), 167 deletions(-)

2.35.1

From: Thomas Huth <thuth@redhat.com>

By using subdir_done(), we can get rid of one level of indentation

in this file. This will make it easier to add more conditions to

skip the iotests in future patches.

Reviewed-by: Hanna Reitz <hreitz@redhat.com>

Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>

Signed-off-by: Thomas Huth <thuth@redhat.com>

Message-Id: <20220223093840.2515281-3-thuth@redhat.com>

Signed-off-by: Hanna Reitz <hreitz@redhat.com>

tests/qemu-iotests/meson.build | 61 ++++++++++++++++++----------------

1 file changed, 32 insertions(+), 29 deletions(-)

diff --git a/tests/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build

--- a/tests/qemu-iotests/meson.build

+++ b/tests/qemu-iotests/meson.build

@@ -XXX,XX +XXX,XX @@

-if have_tools and targetos != 'windows' and not get_option('gprof')

- qemu_iotests_binaries = [qemu_img, qemu_io, qemu_nbd, qsd]

- qemu_iotests_env = {'PYTHON': python.full_path()}

- qemu_iotests_formats = {

- 'qcow2': 'quick',

- 'raw': 'slow',

- 'qed': 'thorough',

- 'vmdk': 'thorough',

- 'vpc': 'thorough'

- }

-

- foreach k, v : emulators

- if k.startswith('qemu-system-')

- qemu_iotests_binaries += v

- endif

- endforeach

- foreach format, speed: qemu_iotests_formats

- if speed == 'quick'

- suites = 'block'

- else

- suites = ['block-' + speed, speed]

- endif

- test('qemu-iotests ' + format, sh, args: [files('../check-block.sh'), format],

- depends: qemu_iotests_binaries, env: qemu_iotests_env,

- protocol: 'tap',

- suite: suites,

- timeout: 0,

- is_parallel: false)

- endforeach

+if not have_tools or targetos == 'windows' or get_option('gprof')

+ subdir_done()

endif

+qemu_iotests_binaries = [qemu_img, qemu_io, qemu_nbd, qsd]

+qemu_iotests_env = {'PYTHON': python.full_path()}

+qemu_iotests_formats = {

+ 'qcow2': 'quick',

+ 'raw': 'slow',

+ 'qed': 'thorough',

+ 'vmdk': 'thorough',

+ 'vpc': 'thorough'

+foreach k, v : emulators

+ if k.startswith('qemu-system-')

+ qemu_iotests_binaries += v

+ endif

+endforeach

+

+foreach format, speed: qemu_iotests_formats

+ if speed == 'quick'

+ suites = 'block'

+ else

+ suites = ['block-' + speed, speed]

+ endif

+ test('qemu-iotests ' + format, sh, args: [files('../check-block.sh'), format],

+ depends: qemu_iotests_binaries, env: qemu_iotests_env,

+ protocol: 'tap',

+ suite: suites,

+ timeout: 0,

+ is_parallel: false)

+endforeach

2.35.1

From: Thomas Huth <thuth@redhat.com>

We want to get rid of check-block.sh in the long run, so let's move

the checks for the bash version and sanitizers from check-block.sh

into the meson.build file instead.

Signed-off-by: Thomas Huth <thuth@redhat.com>

Message-Id: <20220223093840.2515281-4-thuth@redhat.com>

Signed-off-by: Hanna Reitz <hreitz@redhat.com>

---

tests/check-block.sh | 26 --------------------------

tests/qemu-iotests/meson.build | 14 ++++++++++++++

2 files changed, 14 insertions(+), 26 deletions(-)

diff --git a/tests/check-block.sh b/tests/check-block.sh

index XXXXXXX..XXXXXXX 100755

--- a/tests/check-block.sh

+++ b/tests/check-block.sh

@@ -XXX,XX +XXX,XX @@ skip() {

exit 0

}

-# Disable tests with any sanitizer except for specific ones

-SANITIZE_FLAGS=$( grep "CFLAGS.*-fsanitize" config-host.mak 2>/dev/null )

-ALLOWED_SANITIZE_FLAGS="safe-stack cfi-icall"

-#Remove all occurrencies of allowed Sanitize flags

-for j in ${ALLOWED_SANITIZE_FLAGS}; do

- TMP_FLAGS=${SANITIZE_FLAGS}

- SANITIZE_FLAGS=""

- for i in ${TMP_FLAGS}; do

- if ! echo ${i} | grep -q "${j}" 2>/dev/null; then

- SANITIZE_FLAGS="${SANITIZE_FLAGS} ${i}"

- fi

- done

-done

-if echo ${SANITIZE_FLAGS} | grep -q "\-fsanitize" 2>/dev/null; then

- # Have a sanitize flag that is not allowed, stop

- skip "Sanitizers are enabled ==> Not running the qemu-iotests."

-fi

-

if [ -z "$(find . -name 'qemu-system-*' -print)" ]; then

skip "No qemu-system binary available ==> Not running the qemu-iotests."

fi

-if ! command -v bash >/dev/null 2>&1 ; then

- skip "bash not available ==> Not running the qemu-iotests."

-fi

-

-if LANG=C bash --version | grep -q 'GNU bash, version [123]' ; then

- skip "bash version too old ==> Not running the qemu-iotests."

-fi

-

cd tests/qemu-iotests

# QEMU_CHECK_BLOCK_AUTO is used to disable some unstable sub-tests

diff --git a/tests/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build

--- a/tests/qemu-iotests/meson.build

+++ b/tests/qemu-iotests/meson.build

@@ -XXX,XX +XXX,XX @@ if not have_tools or targetos == 'windows' or get_option('gprof')

subdir_done()

endif

+foreach cflag: config_host['QEMU_CFLAGS'].split()

+ if cflag.startswith('-fsanitize') and \

+ not cflag.contains('safe-stack') and not cflag.contains('cfi-icall')

+ message('Sanitizers are enabled ==> Disabled the qemu-iotests.')

+ subdir_done()

+ endif

+endforeach

+bash = find_program('bash', required: false, version: '>= 4.0')

+if not bash.found()

+ message('bash >= v4.0 not available ==> Disabled the qemu-iotests.')

+ subdir_done()

+endif

qemu_iotests_binaries = [qemu_img, qemu_io, qemu_nbd, qsd]

qemu_iotests_env = {'PYTHON': python.full_path()}

qemu_iotests_formats = {

2.35.1

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

Signed-off-by: Hanna Reitz <hreitz@redhat.com>

Message-Id: <20220323105522.53660-2-hreitz@redhat.com>

Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>

---

tests/qemu-iotests/iotests.py | 20 ++++++++++++++++++++

1 file changed, 20 insertions(+)

diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py

--- a/tests/qemu-iotests/iotests.py

+++ b/tests/qemu-iotests/iotests.py

@@ -XXX,XX +XXX,XX @@ def verify_working_luks():

if not working:

notrun(reason)

+def supports_qcow2_zstd_compression() -> bool:

+ img_file = f'{test_dir}/qcow2-zstd-test.qcow2'

+ res = qemu_img('create', '-f', 'qcow2', '-o', 'compression_type=zstd',

+ img_file, '0',

+ check=False)

+ try:

+ os.remove(img_file)

+ except OSError:

+ pass

+

+ if res.returncode == 1 and \

+ "'compression-type' does not accept value 'zstd'" in res.stdout:

+ return False

+ else:

+ return True

+

+def verify_qcow2_zstd_compression():

+ if not supports_qcow2_zstd_compression():

+ notrun('zstd compression not supported')

+

def qemu_pipe(*args: str) -> str:

"""

Run qemu with an option to print something and exit (e.g. a help option).

2.35.1

Some test cases run in iotest 065 want to run with zstd compression just

for added coverage. Run them with zlib if there is no zstd support

compiled in.

Reported-by: Thomas Huth <thuth@redhat.com>

Fixes: 12a936171d71f839dc907ff ("iotest 065: explicit compression type")

Signed-off-by: Hanna Reitz <hreitz@redhat.com>

Message-Id: <20220323105522.53660-3-hreitz@redhat.com>

Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>

tests/qemu-iotests/065 | 24 ++++++++++++++++++------

1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/tests/qemu-iotests/065 b/tests/qemu-iotests/065

index XXXXXXX..XXXXXXX 100755

--- a/tests/qemu-iotests/065

+++ b/tests/qemu-iotests/065

@@ -XXX,XX +XXX,XX @@ import os

import re

import json

import iotests

-from iotests import qemu_img, qemu_img_info

+from iotests import qemu_img, qemu_img_info, supports_qcow2_zstd_compression

import unittest

test_img = os.path.join(iotests.test_dir, 'test.img')

@@ -XXX,XX +XXX,XX @@ class TestQCow2(TestQemuImgInfo):

class TestQCow3NotLazy(TestQemuImgInfo):

'''Testing a qcow2 version 3 image with lazy refcounts disabled'''

- img_options = 'compat=1.1,lazy_refcounts=off,compression_type=zstd'

+ if supports_qcow2_zstd_compression():

+ compression_type = 'zstd'

+ else:

+ compression_type = 'zlib'

+

+ img_options = 'compat=1.1,lazy_refcounts=off'

+ img_options += f',compression_type={compression_type}'

json_compare = { 'compat': '1.1', 'lazy-refcounts': False,

'refcount-bits': 16, 'corrupt': False,

- 'compression-type': 'zstd', 'extended-l2': False }

- human_compare = [ 'compat: 1.1', 'compression type: zstd',

+ 'compression-type': compression_type, 'extended-l2': False }

+ human_compare = [ 'compat: 1.1', f'compression type: {compression_type}',

'lazy refcounts: false', 'refcount bits: 16',

'corrupt: false', 'extended l2: false' ]

@@ -XXX,XX +XXX,XX @@ class TestQCow3NotLazyQMP(TestQMP):

class TestQCow3LazyQMP(TestQMP):

'''Testing a qcow2 version 3 image with lazy refcounts enabled, opening

with lazy refcounts disabled'''

- img_options = 'compat=1.1,lazy_refcounts=on,compression_type=zstd'

+ if supports_qcow2_zstd_compression():

+ compression_type = 'zstd'

+ else:

+ compression_type = 'zlib'

+

+ img_options = 'compat=1.1,lazy_refcounts=on'

+ img_options += f',compression_type={compression_type}'

qemu_options = 'lazy-refcounts=off'

compare = { 'compat': '1.1', 'lazy-refcounts': True,

'refcount-bits': 16, 'corrupt': False,

- 'compression-type': 'zstd', 'extended-l2': False }

+ 'compression-type': compression_type, 'extended-l2': False }

TestImageInfoSpecific = None

TestQemuImgInfo = None

2.35.1

303 runs two test cases, one of which requires zstd support.

Unfortunately, given that this is not a unittest-style test, we cannot

easily skip that single case, and instead can only skip the whole test.

(Alternatively, we could split this test into a zlib and a zstd part,

but that seems excessive, given that this test is not in auto and thus

likely only run by developers who have zstd support compiled in.)

Fixes: 677e0bae686e7c670a71d1f ("iotest 303: explicit compression type")

Signed-off-by: Hanna Reitz <hreitz@redhat.com>

Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>

Message-Id: <20220323105522.53660-4-hreitz@redhat.com>

tests/qemu-iotests/303 | 4 +++-

diff --git a/tests/qemu-iotests/303 b/tests/qemu-iotests/303

--- a/tests/qemu-iotests/303

+++ b/tests/qemu-iotests/303

import iotests

-from iotests import qemu_img_create, qemu_io, file_path, log, filter_qemu_io

+from iotests import qemu_img_create, qemu_io, file_path, log, filter_qemu_io, \

+ verify_qcow2_zstd_compression

iotests.script_initialize(supported_fmts=['qcow2'],

unsupported_imgopts=['refcount_bits', 'compat'])

+verify_qcow2_zstd_compression()

disk = file_path('disk')

chunk = 1024 * 1024

2.35.1

When rebuilding the refcount structures (when qemu-img check -r found

errors with refcount = 0, but reference count > 0), the new refcount

table defaults to being put at the image file end[1]. There is no good

reason for that except that it means we will not have to rewrite any

refblocks we already wrote to disk.

Changing the code to rewrite those refblocks is not too difficult,

though, so let us do that. That is beneficial for images on block

devices, where we cannot really write beyond the end of the image file.

Use this opportunity to add extensive comments to the code, and refactor

it a bit, getting rid of the backwards-jumping goto.

[1] Unless there is something allocated in the area pointed to by the

last refblock, so we have to write that refblock. In that case, we

try to put the reftable in there.

Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1519071

Closes: https://gitlab.com/qemu-project/qemu/-/issues/941

Reviewed-by: Eric Blake <eblake@redhat.com>

Signed-off-by: Hanna Reitz <hreitz@redhat.com>

Message-Id: <20220405134652.19278-2-hreitz@redhat.com>

block/qcow2-refcount.c | 332 +++++++++++++++++++++++++++++------------

1 file changed, 235 insertions(+), 97 deletions(-)

diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c

--- a/block/qcow2-refcount.c

+++ b/block/qcow2-refcount.c

@@ -XXX,XX +XXX,XX @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs,

}

/*

- * Creates a new refcount structure based solely on the in-memory information

- * given through *refcount_table. All necessary allocations will be reflected

- * in that array.

+ * Helper function for rebuild_refcount_structure().

*

- * On success, the old refcount structure is leaked (it will be covered by the

- * new refcount structure).

+ * Scan the range of clusters [first_cluster, end_cluster) for allocated

+ * clusters and write all corresponding refblocks to disk. The refblock

+ * and allocation data is taken from the in-memory refcount table

+ * *refcount_table[] (of size *nb_clusters), which is basically one big

+ * (unlimited size) refblock for the whole image.

+ *

+ * For these refblocks, clusters are allocated using said in-memory

+ * refcount table. Care is taken that these allocations are reflected

+ * in the refblocks written to disk.

+ *

+ * The refblocks' offsets are written into a reftable, which is

+ * *on_disk_reftable_ptr[] (of size *on_disk_reftable_entries_ptr). If

+ * that reftable is of insufficient size, it will be resized to fit.

+ * This reftable is not written to disk.

+ *

+ * (If *on_disk_reftable_ptr is not NULL, the entries within are assumed

+ * to point to existing valid refblocks that do not need to be allocated

+ * again.)

+ *

+ * Return whether the on-disk reftable array was resized (true/false),

+ * or -errno on error.

*/

-static int rebuild_refcount_structure(BlockDriverState *bs,

- BdrvCheckResult *res,

- void **refcount_table,

- int64_t *nb_clusters)

+static int rebuild_refcounts_write_refblocks(

+ BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters,

+ int64_t first_cluster, int64_t end_cluster,

+ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr

+ )

BDRVQcow2State *s = bs->opaque;

- int64_t first_free_cluster = 0, reftable_offset = -1, cluster = 0;

+ int64_t cluster;

int64_t refblock_offset, refblock_start, refblock_index;

- uint32_t reftable_size = 0;

- uint64_t *on_disk_reftable = NULL;

+ int64_t first_free_cluster = 0;

+ uint64_t *on_disk_reftable = *on_disk_reftable_ptr;

+ uint32_t on_disk_reftable_entries = *on_disk_reftable_entries_ptr;

void *on_disk_refblock;

- int ret = 0;

- struct {

- uint64_t reftable_offset;

- uint32_t reftable_clusters;

- } QEMU_PACKED reftable_offset_and_clusters;

-

- qcow2_cache_empty(bs, s->refcount_block_cache);

+ bool reftable_grown = false;

+ int ret;

-write_refblocks:

- for (; cluster < *nb_clusters; cluster++) {

+ for (cluster = first_cluster; cluster < end_cluster; cluster++) {

+ /* Check all clusters to find refblocks that contain non-zero entries */

if (!s->get_refcount(*refcount_table, cluster)) {

continue;

}

+ /*

+ * This cluster is allocated, so we need to create a refblock

+ * for it. The data we will write to disk is just the

+ * respective slice from *refcount_table, so it will contain

+ * accurate refcounts for all clusters belonging to this

+ * refblock. After we have written it, we will therefore skip

+ * all remaining clusters in this refblock.

+ */

+

refblock_index = cluster >> s->refcount_block_bits;

refblock_start = refblock_index << s->refcount_block_bits;

- /* Don't allocate a cluster in a refblock already written to disk */

- if (first_free_cluster < refblock_start) {

- first_free_cluster = refblock_start;

- }

- refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table,

- nb_clusters, &first_free_cluster);

- if (refblock_offset < 0) {

- fprintf(stderr, "ERROR allocating refblock: %s\n",

- strerror(-refblock_offset));

- res->check_errors++;

- ret = refblock_offset;

- goto fail;

- }

+ if (on_disk_reftable_entries > refblock_index &&

+ on_disk_reftable[refblock_index])

+ {

+ /*

+ * We can get here after a `goto write_refblocks`: We have a

+ * reftable from a previous run, and the refblock is already

+ * allocated. No need to allocate it again.

+ */

+ refblock_offset = on_disk_reftable[refblock_index];

+ } else {

+ int64_t refblock_cluster_index;

- if (reftable_size <= refblock_index) {

- uint32_t old_reftable_size = reftable_size;

- uint64_t *new_on_disk_reftable;

+ /* Don't allocate a cluster in a refblock already written to disk */

+ if (first_free_cluster < refblock_start) {

+ first_free_cluster = refblock_start;

+ }

+ refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table,

+ nb_clusters,

+ &first_free_cluster);

+ if (refblock_offset < 0) {

+ fprintf(stderr, "ERROR allocating refblock: %s\n",

+ strerror(-refblock_offset));

+ return refblock_offset;

+ }

- reftable_size = ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE,

- s->cluster_size) / REFTABLE_ENTRY_SIZE;

- new_on_disk_reftable = g_try_realloc(on_disk_reftable,

- reftable_size *

- REFTABLE_ENTRY_SIZE);

- if (!new_on_disk_reftable) {

- res->check_errors++;

- ret = -ENOMEM;

- goto fail;

+ refblock_cluster_index = refblock_offset / s->cluster_size;

+ if (refblock_cluster_index >= end_cluster) {

+ /*

+ * We must write the refblock that holds this refblock's

+ * refcount

+ */

+ end_cluster = refblock_cluster_index + 1;

}

- on_disk_reftable = new_on_disk_reftable;

- memset(on_disk_reftable + old_reftable_size, 0,

- (reftable_size - old_reftable_size) * REFTABLE_ENTRY_SIZE);

+ if (on_disk_reftable_entries <= refblock_index) {

+ on_disk_reftable_entries =

+ ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE,

+ s->cluster_size) / REFTABLE_ENTRY_SIZE;

+ on_disk_reftable =

+ g_try_realloc(on_disk_reftable,

+ on_disk_reftable_entries *

+ REFTABLE_ENTRY_SIZE);

+ if (!on_disk_reftable) {

+ return -ENOMEM;

+ }

- /* The offset we have for the reftable is now no longer valid;

- * this will leak that range, but we can easily fix that by running

- * a leak-fixing check after this rebuild operation */

- reftable_offset = -1;

- } else {

- assert(on_disk_reftable);

- }

- on_disk_reftable[refblock_index] = refblock_offset;

+ memset(on_disk_reftable + *on_disk_reftable_entries_ptr, 0,

+ (on_disk_reftable_entries -

+ *on_disk_reftable_entries_ptr) *

+ REFTABLE_ENTRY_SIZE);

- /* If this is apparently the last refblock (for now), try to squeeze the

- * reftable in */

- if (refblock_index == (*nb_clusters - 1) >> s->refcount_block_bits &&

- reftable_offset < 0)

- {

- uint64_t reftable_clusters = size_to_clusters(s, reftable_size *

- REFTABLE_ENTRY_SIZE);

- reftable_offset = alloc_clusters_imrt(bs, reftable_clusters,

- refcount_table, nb_clusters,

- &first_free_cluster);

- if (reftable_offset < 0) {

- fprintf(stderr, "ERROR allocating reftable: %s\n",

- strerror(-reftable_offset));

- res->check_errors++;

- ret = reftable_offset;

- goto fail;

+ *on_disk_reftable_ptr = on_disk_reftable;

+ *on_disk_reftable_entries_ptr = on_disk_reftable_entries;

+

+ reftable_grown = true;

+ } else {

+ assert(on_disk_reftable);

}

+ on_disk_reftable[refblock_index] = refblock_offset;

}

+ /* Refblock is allocated, write it to disk */

+

ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset,

s->cluster_size, false);

if (ret < 0) {

fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));

- goto fail;

+ return ret;

}

- /* The size of *refcount_table is always cluster-aligned, therefore the

- * write operation will not overflow */

+ /*

+ * The refblock is simply a slice of *refcount_table.

+ * Note that the size of *refcount_table is always aligned to

+ * whole clusters, so the write operation will not result in

+ * out-of-bounds accesses.

+ */

on_disk_refblock = (void *)((char *) *refcount_table +

refblock_index * s->cluster_size);

@@ -XXX,XX +XXX,XX @@ write_refblocks:

s->cluster_size);

if (ret < 0) {

fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));

- goto fail;

+ return ret;

}

- /* Go to the end of this refblock */

+ /* This refblock is done, skip to its end */

cluster = refblock_start + s->refcount_block_size - 1;

- if (reftable_offset < 0) {

- uint64_t post_refblock_start, reftable_clusters;

+ return reftable_grown;

+}

+

+/*

+ * Creates a new refcount structure based solely on the in-memory information

+ * given through *refcount_table (this in-memory information is basically just

+ * the concatenation of all refblocks). All necessary allocations will be

+ * reflected in that array.

+ *

+ * On success, the old refcount structure is leaked (it will be covered by the

+ * new refcount structure).

+ */

+static int rebuild_refcount_structure(BlockDriverState *bs,

+ BdrvCheckResult *res,

+ void **refcount_table,

+ int64_t *nb_clusters)

+{

+ BDRVQcow2State *s = bs->opaque;

+ int64_t reftable_offset = -1;

+ int64_t reftable_length = 0;

+ int64_t reftable_clusters;

+ int64_t refblock_index;

+ uint32_t on_disk_reftable_entries = 0;

+ uint64_t *on_disk_reftable = NULL;

+ int ret = 0;

+ int reftable_size_changed = 0;

+ struct {

+ uint64_t reftable_offset;

+ uint32_t reftable_clusters;

+ } QEMU_PACKED reftable_offset_and_clusters;

+

+ qcow2_cache_empty(bs, s->refcount_block_cache);

+

+ /*

+ * For each refblock containing entries, we try to allocate a

+ * cluster (in the in-memory refcount table) and write its offset

+ * into on_disk_reftable[]. We then write the whole refblock to

+ * disk (as a slice of the in-memory refcount table).

+ * This is done by rebuild_refcounts_write_refblocks().

+ *

+ * Once we have scanned all clusters, we try to find space for the

+ * reftable. This will dirty the in-memory refcount table (i.e.

+ * make it differ from the refblocks we have already written), so we

+ * need to run rebuild_refcounts_write_refblocks() again for the

+ * range of clusters where the reftable has been allocated.

+ *

+ * This second run might make the reftable grow again, in which case

+ * we will need to allocate another space for it, which is why we

+ * repeat all this until the reftable stops growing.

+ *

+ * (This loop will terminate, because with every cluster the

+ * reftable grows, it can accomodate a multitude of more refcounts,

+ * so that at some point this must be able to cover the reftable

+ * and all refblocks describing it.)

+ *

+ * We then convert the reftable to big-endian and write it to disk.

+ *

+ * Note that we never free any reftable allocations. Doing so would

+ * needlessly complicate the algorithm: The eventual second check

+ * run we do will clean up all leaks we have caused.

+ */

+

+ reftable_size_changed =

+ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,

+ 0, *nb_clusters,

+ &on_disk_reftable,

+ &on_disk_reftable_entries);

+ if (reftable_size_changed < 0) {

+ res->check_errors++;

+ ret = reftable_size_changed;

+ goto fail;

+ /*

+ * There was no reftable before, so rebuild_refcounts_write_refblocks()

+ * must have increased its size (from 0 to something).

+ */

+ assert(reftable_size_changed);

+

+ do {

+ int64_t reftable_start_cluster, reftable_end_cluster;

+ int64_t first_free_cluster = 0;

+

+ reftable_length = on_disk_reftable_entries * REFTABLE_ENTRY_SIZE;

+ reftable_clusters = size_to_clusters(s, reftable_length);

- post_refblock_start = ROUND_UP(*nb_clusters, s->refcount_block_size);

- reftable_clusters =

- size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE);

- /* Not pretty but simple */

- if (first_free_cluster < post_refblock_start) {

- first_free_cluster = post_refblock_start;

- }

reftable_offset = alloc_clusters_imrt(bs, reftable_clusters,

refcount_table, nb_clusters,

&first_free_cluster);

@@ -XXX,XX +XXX,XX @@ write_refblocks:

goto fail;

}

- goto write_refblocks;

- }

+ /*

+ * We need to update the affected refblocks, so re-run the

+ * write_refblocks loop for the reftable's range of clusters.

+ */

+ assert(offset_into_cluster(s, reftable_offset) == 0);

+ reftable_start_cluster = reftable_offset / s->cluster_size;

+ reftable_end_cluster = reftable_start_cluster + reftable_clusters;

+ reftable_size_changed =

+ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,

+ reftable_start_cluster,

+ reftable_end_cluster,

+ &on_disk_reftable,

+ &on_disk_reftable_entries);

+ if (reftable_size_changed < 0) {

+ res->check_errors++;

+ ret = reftable_size_changed;

+ goto fail;

+ }

+

+ /*

+ * If the reftable size has changed, we will need to find a new

+ * allocation, repeating the loop.

+ */

+ } while (reftable_size_changed);

- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {

+ /* The above loop must have run at least once */

+ assert(reftable_offset >= 0);

+

+ /*

+ * All allocations are done, all refblocks are written, convert the

+ * reftable to big-endian and write it to disk.

+ */

+

+ for (refblock_index = 0; refblock_index < on_disk_reftable_entries;

+ refblock_index++)

+ {

cpu_to_be64s(&on_disk_reftable[refblock_index]);

- ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset,

- reftable_size * REFTABLE_ENTRY_SIZE,

+ ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length,

false);

if (ret < 0) {

fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));

goto fail;

- assert(reftable_size < INT_MAX / REFTABLE_ENTRY_SIZE);

+ assert(reftable_length < INT_MAX);

ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,

- reftable_size * REFTABLE_ENTRY_SIZE);

+ reftable_length);

if (ret < 0) {

fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));

goto fail;

@@ -XXX,XX +XXX,XX @@ write_refblocks:

/* Enter new reftable into the image header */

reftable_offset_and_clusters.reftable_offset = cpu_to_be64(reftable_offset);

reftable_offset_and_clusters.reftable_clusters =

- cpu_to_be32(size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE));

+ cpu_to_be32(reftable_clusters);

ret = bdrv_pwrite_sync(bs->file,

offsetof(QCowHeader, refcount_table_offset),

&reftable_offset_and_clusters,

@@ -XXX,XX +XXX,XX @@ write_refblocks:

goto fail;

}

- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {

+ for (refblock_index = 0; refblock_index < on_disk_reftable_entries;

+ refblock_index++)

+ {

be64_to_cpus(&on_disk_reftable[refblock_index]);

}

s->refcount_table = on_disk_reftable;

s->refcount_table_offset = reftable_offset;

- s->refcount_table_size = reftable_size;

+ s->refcount_table_size = on_disk_reftable_entries;

update_max_refcount_table_index(s);

return 0;

2.35.1