1
The following changes since commit 1be5a765c08cee3a9587c8a8d3fc2ea247b13f9c:
1
The following changes since commit 474f3938d79ab36b9231c9ad3b5a9314c2aeacde:
2
2
3
Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2022-04-19 18:22:16 -0700)
3
Merge remote-tracking branch 'remotes/amarkovic/tags/mips-queue-jun-21-2019' into staging (2019-06-21 15:40:50 +0100)
4
4
5
are available in the Git repository at:
5
are available in the Git repository at:
6
6
7
https://gitlab.com/hreitz/qemu.git tags/pull-block-2022-04-20
7
https://github.com/XanClic/qemu.git tags/pull-block-2019-06-24
8
8
9
for you to fetch changes up to 0423f75351ab83b844a31349218b0eadd830e07a:
9
for you to fetch changes up to ab5d4a30f7f3803ca5106b370969c1b7b54136f8:
10
10
11
qcow2: Add errp to rebuild_refcount_structure() (2022-04-20 12:09:17 +0200)
11
iotests: Fix 205 for concurrent runs (2019-06-24 16:01:40 +0200)
12
12
13
----------------------------------------------------------------
13
----------------------------------------------------------------
14
Block patches:
14
Block patches:
15
- Some changes for qcow2's refcount repair algorithm to make it work for
15
- The SSH block driver now uses libssh instead of libssh2
16
qcow2 images stored on block devices
16
- The VMDK block driver gets read-only support for the seSparse
17
- Skip test cases that require zstd when support for it is missing
17
subformat
18
- Some refactoring in the iotests' meson.build
18
- Various fixes
19
20
---
21
22
v2:
23
- Squashed Pino's fix for pre-0.8 libssh into the libssh patch
19
24
20
----------------------------------------------------------------
25
----------------------------------------------------------------
21
Hanna Reitz (6):
26
Anton Nefedov (1):
22
iotests.py: Add supports_qcow2_zstd_compression()
27
iotest 134: test cluster-misaligned encrypted write
23
iotests/065: Check for zstd support
24
iotests/303: Check for zstd support
25
qcow2: Improve refcount structure rebuilding
26
iotests/108: Test new refcount rebuild algorithm
27
qcow2: Add errp to rebuild_refcount_structure()
28
28
29
Thomas Huth (2):
29
Klaus Birkelund Jensen (1):
30
tests/qemu-iotests/meson.build: Improve the indentation
30
nvme: do not advertise support for unsupported arbitration mechanism
31
tests/qemu-iotests: Move the bash and sanitizer checks to meson.build
32
31
33
block/qcow2-refcount.c | 353 +++++++++++++++++++++++----------
32
Max Reitz (1):
34
tests/check-block.sh | 26 ---
33
iotests: Fix 205 for concurrent runs
35
tests/qemu-iotests/065 | 24 ++-
34
36
tests/qemu-iotests/108 | 259 +++++++++++++++++++++++-
35
Pino Toscano (1):
37
tests/qemu-iotests/108.out | 81 ++++++++
36
ssh: switch from libssh2 to libssh
38
tests/qemu-iotests/303 | 4 +-
37
39
tests/qemu-iotests/iotests.py | 20 ++
38
Sam Eiderman (3):
40
tests/qemu-iotests/meson.build | 73 ++++---
39
vmdk: Fix comment regarding max l1_size coverage
41
8 files changed, 673 insertions(+), 167 deletions(-)
40
vmdk: Reduce the max bound for L1 table size
41
vmdk: Add read-only support for seSparse snapshots
42
43
Vladimir Sementsov-Ogievskiy (1):
44
blockdev: enable non-root nodes for transaction drive-backup source
45
46
configure | 65 +-
47
block/Makefile.objs | 6 +-
48
block/ssh.c | 652 ++++++++++--------
49
block/vmdk.c | 372 +++++++++-
50
blockdev.c | 2 +-
51
hw/block/nvme.c | 1 -
52
.travis.yml | 4 +-
53
block/trace-events | 14 +-
54
docs/qemu-block-drivers.texi | 2 +-
55
.../dockerfiles/debian-win32-cross.docker | 1 -
56
.../dockerfiles/debian-win64-cross.docker | 1 -
57
tests/docker/dockerfiles/fedora.docker | 4 +-
58
tests/docker/dockerfiles/ubuntu.docker | 2 +-
59
tests/docker/dockerfiles/ubuntu1804.docker | 2 +-
60
tests/qemu-iotests/059.out | 2 +-
61
tests/qemu-iotests/134 | 9 +
62
tests/qemu-iotests/134.out | 10 +
63
tests/qemu-iotests/205 | 2 +-
64
tests/qemu-iotests/207 | 54 +-
65
tests/qemu-iotests/207.out | 2 +-
66
20 files changed, 823 insertions(+), 384 deletions(-)
42
67
43
--
68
--
44
2.35.1
69
2.21.0
70
71
diff view generated by jsdifflib
1
303 runs two test cases, one of which requires zstd support.
1
From: Klaus Birkelund Jensen <klaus@birkelund.eu>
2
Unfortunately, given that this is not a unittest-style test, we cannot
3
easily skip that single case, and instead can only skip the whole test.
4
2
5
(Alternatively, we could split this test into a zlib and a zstd part,
3
The device mistakenly reports that the Weighted Round Robin with Urgent
6
but that seems excessive, given that this test is not in auto and thus
4
Priority Class arbitration mechanism is supported.
7
likely only run by developers who have zstd support compiled in.)
8
5
9
Fixes: 677e0bae686e7c670a71d1f ("iotest 303: explicit compression type")
6
It is not.
10
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
7
11
Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>
8
Signed-off-by: Klaus Birkelund Jensen <klaus.jensen@cnexlabs.com>
12
Message-Id: <20220323105522.53660-4-hreitz@redhat.com>
9
Message-id: 20190606092530.14206-1-klaus@birkelund.eu
10
Acked-by: Maxim Levitsky <mlevitsk@redhat.com>
11
Signed-off-by: Max Reitz <mreitz@redhat.com>
13
---
12
---
14
tests/qemu-iotests/303 | 4 +++-
13
hw/block/nvme.c | 1 -
15
1 file changed, 3 insertions(+), 1 deletion(-)
14
1 file changed, 1 deletion(-)
16
15
17
diff --git a/tests/qemu-iotests/303 b/tests/qemu-iotests/303
16
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
18
index XXXXXXX..XXXXXXX 100755
17
index XXXXXXX..XXXXXXX 100644
19
--- a/tests/qemu-iotests/303
18
--- a/hw/block/nvme.c
20
+++ b/tests/qemu-iotests/303
19
+++ b/hw/block/nvme.c
21
@@ -XXX,XX +XXX,XX @@
20
@@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
22
21
n->bar.cap = 0;
23
import iotests
22
NVME_CAP_SET_MQES(n->bar.cap, 0x7ff);
24
import subprocess
23
NVME_CAP_SET_CQR(n->bar.cap, 1);
25
-from iotests import qemu_img_create, qemu_io, file_path, log, filter_qemu_io
24
- NVME_CAP_SET_AMS(n->bar.cap, 1);
26
+from iotests import qemu_img_create, qemu_io, file_path, log, filter_qemu_io, \
25
NVME_CAP_SET_TO(n->bar.cap, 0xf);
27
+ verify_qcow2_zstd_compression
26
NVME_CAP_SET_CSS(n->bar.cap, 1);
28
27
NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
29
iotests.script_initialize(supported_fmts=['qcow2'],
30
unsupported_imgopts=['refcount_bits', 'compat'])
31
+verify_qcow2_zstd_compression()
32
33
disk = file_path('disk')
34
chunk = 1024 * 1024
35
--
28
--
36
2.35.1
29
2.21.0
30
31
diff view generated by jsdifflib
1
Some test cases run in iotest 065 want to run with zstd compression just
1
From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
2
for added coverage. Run them with zlib if there is no zstd support
3
compiled in.
4
2
5
Reported-by: Thomas Huth <thuth@redhat.com>
3
We forget to enable it for transaction .prepare, while it is already
6
Fixes: 12a936171d71f839dc907ff ("iotest 065: explicit compression type")
4
enabled in do_drive_backup since commit a2d665c1bc362
7
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
5
"blockdev: loosen restrictions on drive-backup source node"
8
Message-Id: <20220323105522.53660-3-hreitz@redhat.com>
6
9
Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>
7
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
8
Message-id: 20190618140804.59214-1-vsementsov@virtuozzo.com
9
Reviewed-by: John Snow <jsnow@redhat.com>
10
Signed-off-by: Max Reitz <mreitz@redhat.com>
10
---
11
---
11
tests/qemu-iotests/065 | 24 ++++++++++++++++++------
12
blockdev.c | 2 +-
12
1 file changed, 18 insertions(+), 6 deletions(-)
13
1 file changed, 1 insertion(+), 1 deletion(-)
13
14
14
diff --git a/tests/qemu-iotests/065 b/tests/qemu-iotests/065
15
diff --git a/blockdev.c b/blockdev.c
15
index XXXXXXX..XXXXXXX 100755
16
index XXXXXXX..XXXXXXX 100644
16
--- a/tests/qemu-iotests/065
17
--- a/blockdev.c
17
+++ b/tests/qemu-iotests/065
18
+++ b/blockdev.c
18
@@ -XXX,XX +XXX,XX @@ import os
19
@@ -XXX,XX +XXX,XX @@ static void drive_backup_prepare(BlkActionState *common, Error **errp)
19
import re
20
assert(common->action->type == TRANSACTION_ACTION_KIND_DRIVE_BACKUP);
20
import json
21
backup = common->action->u.drive_backup.data;
21
import iotests
22
22
-from iotests import qemu_img, qemu_img_info
23
- bs = qmp_get_root_bs(backup->device, errp);
23
+from iotests import qemu_img, qemu_img_info, supports_qcow2_zstd_compression
24
+ bs = bdrv_lookup_bs(backup->device, backup->device, errp);
24
import unittest
25
if (!bs) {
25
26
return;
26
test_img = os.path.join(iotests.test_dir, 'test.img')
27
}
27
@@ -XXX,XX +XXX,XX @@ class TestQCow2(TestQemuImgInfo):
28
29
class TestQCow3NotLazy(TestQemuImgInfo):
30
'''Testing a qcow2 version 3 image with lazy refcounts disabled'''
31
- img_options = 'compat=1.1,lazy_refcounts=off,compression_type=zstd'
32
+ if supports_qcow2_zstd_compression():
33
+ compression_type = 'zstd'
34
+ else:
35
+ compression_type = 'zlib'
36
+
37
+ img_options = 'compat=1.1,lazy_refcounts=off'
38
+ img_options += f',compression_type={compression_type}'
39
json_compare = { 'compat': '1.1', 'lazy-refcounts': False,
40
'refcount-bits': 16, 'corrupt': False,
41
- 'compression-type': 'zstd', 'extended-l2': False }
42
- human_compare = [ 'compat: 1.1', 'compression type: zstd',
43
+ 'compression-type': compression_type, 'extended-l2': False }
44
+ human_compare = [ 'compat: 1.1', f'compression type: {compression_type}',
45
'lazy refcounts: false', 'refcount bits: 16',
46
'corrupt: false', 'extended l2: false' ]
47
48
@@ -XXX,XX +XXX,XX @@ class TestQCow3NotLazyQMP(TestQMP):
49
class TestQCow3LazyQMP(TestQMP):
50
'''Testing a qcow2 version 3 image with lazy refcounts enabled, opening
51
with lazy refcounts disabled'''
52
- img_options = 'compat=1.1,lazy_refcounts=on,compression_type=zstd'
53
+ if supports_qcow2_zstd_compression():
54
+ compression_type = 'zstd'
55
+ else:
56
+ compression_type = 'zlib'
57
+
58
+ img_options = 'compat=1.1,lazy_refcounts=on'
59
+ img_options += f',compression_type={compression_type}'
60
qemu_options = 'lazy-refcounts=off'
61
compare = { 'compat': '1.1', 'lazy-refcounts': True,
62
'refcount-bits': 16, 'corrupt': False,
63
- 'compression-type': 'zstd', 'extended-l2': False }
64
+ 'compression-type': compression_type, 'extended-l2': False }
65
66
TestImageInfoSpecific = None
67
TestQemuImgInfo = None
68
--
28
--
69
2.35.1
29
2.21.0
30
31
diff view generated by jsdifflib
1
Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
1
From: Anton Nefedov <anton.nefedov@virtuozzo.com>
2
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
2
3
Message-Id: <20220323105522.53660-2-hreitz@redhat.com>
3
COW (even empty/zero) areas require encryption too
4
Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>
4
5
Signed-off-by: Anton Nefedov <anton.nefedov@virtuozzo.com>
6
Reviewed-by: Eric Blake <eblake@redhat.com>
7
Reviewed-by: Max Reitz <mreitz@redhat.com>
8
Reviewed-by: Alberto Garcia <berto@igalia.com>
9
Message-id: 20190516143028.81155-1-anton.nefedov@virtuozzo.com
10
Signed-off-by: Max Reitz <mreitz@redhat.com>
5
---
11
---
6
tests/qemu-iotests/iotests.py | 20 ++++++++++++++++++++
12
tests/qemu-iotests/134 | 9 +++++++++
7
1 file changed, 20 insertions(+)
13
tests/qemu-iotests/134.out | 10 ++++++++++
14
2 files changed, 19 insertions(+)
8
15
9
diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
16
diff --git a/tests/qemu-iotests/134 b/tests/qemu-iotests/134
17
index XXXXXXX..XXXXXXX 100755
18
--- a/tests/qemu-iotests/134
19
+++ b/tests/qemu-iotests/134
20
@@ -XXX,XX +XXX,XX @@ echo
21
echo "== reading whole image =="
22
$QEMU_IO --object $SECRET -c "read 0 $size" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
23
24
+echo
25
+echo "== rewriting cluster part =="
26
+$QEMU_IO --object $SECRET -c "write -P 0xb 512 512" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
27
+
28
+echo
29
+echo "== verify pattern =="
30
+$QEMU_IO --object $SECRET -c "read -P 0 0 512" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
31
+$QEMU_IO --object $SECRET -c "read -P 0xb 512 512" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
32
+
33
echo
34
echo "== rewriting whole image =="
35
$QEMU_IO --object $SECRET -c "write -P 0xa 0 $size" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
36
diff --git a/tests/qemu-iotests/134.out b/tests/qemu-iotests/134.out
10
index XXXXXXX..XXXXXXX 100644
37
index XXXXXXX..XXXXXXX 100644
11
--- a/tests/qemu-iotests/iotests.py
38
--- a/tests/qemu-iotests/134.out
12
+++ b/tests/qemu-iotests/iotests.py
39
+++ b/tests/qemu-iotests/134.out
13
@@ -XXX,XX +XXX,XX @@ def verify_working_luks():
40
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on encrypt.
14
if not working:
41
read 134217728/134217728 bytes at offset 0
15
notrun(reason)
42
128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
16
43
17
+def supports_qcow2_zstd_compression() -> bool:
44
+== rewriting cluster part ==
18
+ img_file = f'{test_dir}/qcow2-zstd-test.qcow2'
45
+wrote 512/512 bytes at offset 512
19
+ res = qemu_img('create', '-f', 'qcow2', '-o', 'compression_type=zstd',
46
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
20
+ img_file, '0',
21
+ check=False)
22
+ try:
23
+ os.remove(img_file)
24
+ except OSError:
25
+ pass
26
+
47
+
27
+ if res.returncode == 1 and \
48
+== verify pattern ==
28
+ "'compression-type' does not accept value 'zstd'" in res.stdout:
49
+read 512/512 bytes at offset 0
29
+ return False
50
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
30
+ else:
51
+read 512/512 bytes at offset 512
31
+ return True
52
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
32
+
53
+
33
+def verify_qcow2_zstd_compression():
54
== rewriting whole image ==
34
+ if not supports_qcow2_zstd_compression():
55
wrote 134217728/134217728 bytes at offset 0
35
+ notrun('zstd compression not supported')
56
128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
36
+
37
def qemu_pipe(*args: str) -> str:
38
"""
39
Run qemu with an option to print something and exit (e.g. a help option).
40
--
57
--
41
2.35.1
58
2.21.0
59
60
diff view generated by jsdifflib
1
From: Thomas Huth <thuth@redhat.com>
1
From: Sam Eiderman <shmuel.eiderman@oracle.com>
2
2
3
By using subdir_done(), we can get rid of one level of indentation
3
Commit b0651b8c246d ("vmdk: Move l1_size check into vmdk_add_extent")
4
in this file. This will make it easier to add more conditions to
4
extended the l1_size check from VMDK4 to VMDK3 but did not update the
5
skip the iotests in future patches.
5
default coverage in the moved comment.
6
6
7
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
7
The previous vmdk4 calculation:
8
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
8
9
Signed-off-by: Thomas Huth <thuth@redhat.com>
9
(512 * 1024 * 1024) * 512(l2 entries) * 65536(grain) = 16PB
10
Message-Id: <20220223093840.2515281-3-thuth@redhat.com>
10
11
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
11
The added vmdk3 calculation:
12
13
(512 * 1024 * 1024) * 4096(l2 entries) * 512(grain) = 1PB
14
15
Adding the calculation of vmdk3 to the comment.
16
17
In any case, VMware does not offer virtual disks more than 2TB for
18
vmdk4/vmdk3 or 64TB for the new undocumented seSparse format which is
19
not implemented yet in qemu.
20
21
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
22
Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com>
23
Reviewed-by: Liran Alon <liran.alon@oracle.com>
24
Reviewed-by: Arbel Moshe <arbel.moshe@oracle.com>
25
Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com>
26
Message-id: 20190620091057.47441-2-shmuel.eiderman@oracle.com
27
Reviewed-by: yuchenlin <yuchenlin@synology.com>
28
Reviewed-by: Max Reitz <mreitz@redhat.com>
29
Signed-off-by: Max Reitz <mreitz@redhat.com>
12
---
30
---
13
tests/qemu-iotests/meson.build | 61 ++++++++++++++++++----------------
31
block/vmdk.c | 11 ++++++++---
14
1 file changed, 32 insertions(+), 29 deletions(-)
32
1 file changed, 8 insertions(+), 3 deletions(-)
15
33
16
diff --git a/tests/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build
34
diff --git a/block/vmdk.c b/block/vmdk.c
17
index XXXXXXX..XXXXXXX 100644
35
index XXXXXXX..XXXXXXX 100644
18
--- a/tests/qemu-iotests/meson.build
36
--- a/block/vmdk.c
19
+++ b/tests/qemu-iotests/meson.build
37
+++ b/block/vmdk.c
20
@@ -XXX,XX +XXX,XX @@
38
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
21
-if have_tools and targetos != 'windows' and not get_option('gprof')
39
return -EFBIG;
22
- qemu_iotests_binaries = [qemu_img, qemu_io, qemu_nbd, qsd]
40
}
23
- qemu_iotests_env = {'PYTHON': python.full_path()}
41
if (l1_size > 512 * 1024 * 1024) {
24
- qemu_iotests_formats = {
42
- /* Although with big capacity and small l1_entry_sectors, we can get a
25
- 'qcow2': 'quick',
43
+ /*
26
- 'raw': 'slow',
44
+ * Although with big capacity and small l1_entry_sectors, we can get a
27
- 'qed': 'thorough',
45
* big l1_size, we don't want unbounded value to allocate the table.
28
- 'vmdk': 'thorough',
46
- * Limit it to 512M, which is 16PB for default cluster and L2 table
29
- 'vpc': 'thorough'
47
- * size */
30
- }
48
+ * Limit it to 512M, which is:
31
-
49
+ * 16PB - for default "Hosted Sparse Extent" (VMDK4)
32
- foreach k, v : emulators
50
+ * cluster size: 64KB, L2 table size: 512 entries
33
- if k.startswith('qemu-system-')
51
+ * 1PB - for default "ESXi Host Sparse Extent" (VMDK3/vmfsSparse)
34
- qemu_iotests_binaries += v
52
+ * cluster size: 512B, L2 table size: 4096 entries
35
- endif
53
+ */
36
- endforeach
54
error_setg(errp, "L1 size too big");
37
- foreach format, speed: qemu_iotests_formats
55
return -EFBIG;
38
- if speed == 'quick'
56
}
39
- suites = 'block'
40
- else
41
- suites = ['block-' + speed, speed]
42
- endif
43
- test('qemu-iotests ' + format, sh, args: [files('../check-block.sh'), format],
44
- depends: qemu_iotests_binaries, env: qemu_iotests_env,
45
- protocol: 'tap',
46
- suite: suites,
47
- timeout: 0,
48
- is_parallel: false)
49
- endforeach
50
+if not have_tools or targetos == 'windows' or get_option('gprof')
51
+ subdir_done()
52
endif
53
+
54
+qemu_iotests_binaries = [qemu_img, qemu_io, qemu_nbd, qsd]
55
+qemu_iotests_env = {'PYTHON': python.full_path()}
56
+qemu_iotests_formats = {
57
+ 'qcow2': 'quick',
58
+ 'raw': 'slow',
59
+ 'qed': 'thorough',
60
+ 'vmdk': 'thorough',
61
+ 'vpc': 'thorough'
62
+}
63
+
64
+foreach k, v : emulators
65
+ if k.startswith('qemu-system-')
66
+ qemu_iotests_binaries += v
67
+ endif
68
+endforeach
69
+
70
+foreach format, speed: qemu_iotests_formats
71
+ if speed == 'quick'
72
+ suites = 'block'
73
+ else
74
+ suites = ['block-' + speed, speed]
75
+ endif
76
+ test('qemu-iotests ' + format, sh, args: [files('../check-block.sh'), format],
77
+ depends: qemu_iotests_binaries, env: qemu_iotests_env,
78
+ protocol: 'tap',
79
+ suite: suites,
80
+ timeout: 0,
81
+ is_parallel: false)
82
+endforeach
83
--
57
--
84
2.35.1
58
2.21.0
85
59
86
60
diff view generated by jsdifflib
1
One clear problem with how qcow2's refcount structure rebuild algorithm
1
From: Sam Eiderman <shmuel.eiderman@oracle.com>
2
used to be before "qcow2: Improve refcount structure rebuilding" was
3
that it is prone to failure for qcow2 images on block devices: There is
4
generally unused space after the actual image, and if that exceeds what
5
one refblock covers, the old algorithm would invariably write the
6
reftable past the block device's end, which cannot work. The new
7
algorithm does not have this problem.
8
2
9
Test it with three tests:
3
512M of L1 entries is a very loose bound, only 32M are required to store
10
(1) Create an image with more empty space at the end than what one
4
the maximal supported VMDK file size of 2TB.
11
refblock covers, see whether rebuilding the refcount structures
12
results in a change in the image file length. (It should not.)
13
5
14
(2) Leave precisely enough space somewhere at the beginning of the image
6
Fixed qemu-iotest 59# - now failure occures before on impossible L1
15
for the new reftable (and the refblock for that place), see whether
7
table size.
16
the new algorithm puts the reftable there. (It should.)
17
8
18
(3) Test the original problem: Create (something like) a block device
9
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
19
with a fixed size, then create a qcow2 image in there, write some
10
Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com>
20
data, and then have qemu-img check rebuild the refcount structures.
11
Reviewed-by: Liran Alon <liran.alon@oracle.com>
21
Before HEAD^, the reftable would have been written past the image
12
Reviewed-by: Arbel Moshe <arbel.moshe@oracle.com>
22
file end, i.e. outside of what the block device provides, which
13
Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com>
23
cannot work. HEAD^ should have fixed that.
14
Message-id: 20190620091057.47441-3-shmuel.eiderman@oracle.com
24
("Something like a block device" means a loop device if we can use
15
Reviewed-by: Max Reitz <mreitz@redhat.com>
25
one ("sudo -n losetup" works), or a FUSE block export with
16
Signed-off-by: Max Reitz <mreitz@redhat.com>
26
growable=false otherwise.)
17
---
18
block/vmdk.c | 13 +++++++------
19
tests/qemu-iotests/059.out | 2 +-
20
2 files changed, 8 insertions(+), 7 deletions(-)
27
21
28
Reviewed-by: Eric Blake <eblake@redhat.com>
22
diff --git a/block/vmdk.c b/block/vmdk.c
29
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
30
Message-Id: <20220405134652.19278-3-hreitz@redhat.com>
31
---
32
tests/qemu-iotests/108 | 259 ++++++++++++++++++++++++++++++++++++-
33
tests/qemu-iotests/108.out | 81 ++++++++++++
34
2 files changed, 339 insertions(+), 1 deletion(-)
35
36
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
37
index XXXXXXX..XXXXXXX 100755
38
--- a/tests/qemu-iotests/108
39
+++ b/tests/qemu-iotests/108
40
@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
41
42
_cleanup()
43
{
44
-    _cleanup_test_img
45
+ _cleanup_test_img
46
+ if [ -f "$TEST_DIR/qsd.pid" ]; then
47
+ qsd_pid=$(cat "$TEST_DIR/qsd.pid")
48
+ kill -KILL "$qsd_pid"
49
+ fusermount -u "$TEST_DIR/fuse-export" &>/dev/null
50
+ fi
51
+ rm -f "$TEST_DIR/fuse-export"
52
}
53
trap "_cleanup; exit \$status" 0 1 2 3 15
54
55
# get standard environment, filters and checks
56
. ./common.rc
57
. ./common.filter
58
+. ./common.qemu
59
60
# This tests qcow2-specific low-level functionality
61
_supported_fmt qcow2
62
@@ -XXX,XX +XXX,XX @@ _supported_os Linux
63
# files
64
_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file
65
66
+# This test either needs sudo -n losetup or FUSE exports to work
67
+if sudo -n losetup &>/dev/null; then
68
+ loopdev=true
69
+else
70
+ loopdev=false
71
+
72
+ # QSD --export fuse will either yield "Parameter 'id' is missing"
73
+ # or "Invalid parameter 'fuse'", depending on whether there is
74
+ # FUSE support or not.
75
+ error=$($QSD --export fuse 2>&1)
76
+ if [[ $error = *"'fuse'"* ]]; then
77
+ _notrun 'Passwordless sudo for losetup or FUSE support required, but' \
78
+ 'neither is available'
79
+ fi
80
+fi
81
+
82
echo
83
echo '=== Repairing an image without any refcount table ==='
84
echo
85
@@ -XXX,XX +XXX,XX @@ _make_test_img 64M
86
poke_file "$TEST_IMG" $((0x10008)) "\xff\xff\xff\xff\xff\xff\x00\x00"
87
_check_test_img -r all
88
89
+echo
90
+echo '=== Check rebuilt reftable location ==='
91
+
92
+# In an earlier version of the refcount rebuild algorithm, the
93
+# reftable was generally placed at the image end (unless something was
94
+# allocated in the area covered by the refblock right before the image
95
+# file end, then we would try to place the reftable in that refblock).
96
+# This was later changed so the reftable would be placed in the
97
+# earliest possible location. Test this.
98
+
99
+echo
100
+echo '--- Does the image size increase? ---'
101
+echo
102
+
103
+# First test: Just create some image, write some data to it, and
104
+# resize it so there is free space at the end of the image (enough
105
+# that it spans at least one full refblock, which for cluster_size=512
106
+# images, spans 128k). With the old algorithm, the reftable would
107
+# have then been placed at the end of the image file, but with the new
108
+# one, it will be put in that free space.
109
+# We want to check whether the size of the image file increases due to
110
+# rebuilding the refcount structures (it should not).
111
+
112
+_make_test_img -o 'cluster_size=512' 1M
113
+# Write something
114
+$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
115
+
116
+# Add free space
117
+file_len=$(stat -c '%s' "$TEST_IMG")
118
+truncate -s $((file_len + 256 * 1024)) "$TEST_IMG"
119
+
120
+# Corrupt the image by saying the image header was not allocated
121
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
122
+rb_offset=$(peek_file_be "$TEST_IMG" $rt_offset 8)
123
+poke_file "$TEST_IMG" $rb_offset "\x00\x00"
124
+
125
+# Check whether rebuilding the refcount structures increases the image
126
+# file size
127
+file_len=$(stat -c '%s' "$TEST_IMG")
128
+echo
129
+# The only leaks there can be are the old refcount structures that are
130
+# leaked during rebuilding, no need to clutter the output with them
131
+_check_test_img -r all | grep -v '^Repairing cluster.*refcount=1 reference=0'
132
+echo
133
+post_repair_file_len=$(stat -c '%s' "$TEST_IMG")
134
+
135
+if [[ $file_len -eq $post_repair_file_len ]]; then
136
+ echo 'OK: Image size did not change'
137
+else
138
+ echo 'ERROR: Image size differs' \
139
+ "($file_len before, $post_repair_file_len after)"
140
+fi
141
+
142
+echo
143
+echo '--- Will the reftable occupy a hole specifically left for it? ---'
144
+echo
145
+
146
+# Note: With cluster_size=512, every refblock covers 128k.
147
+# The reftable covers 8M per reftable cluster.
148
+
149
+# Create an image that requires two reftable clusters (just because
150
+# this is more interesting than a single-clustered reftable).
151
+_make_test_img -o 'cluster_size=512' 9M
152
+$QEMU_IO -c 'write 0 8M' "$TEST_IMG" | _filter_qemu_io
153
+
154
+# Writing 8M will have resized the reftable. Unfortunately, doing so
155
+# will leave holes in the file, so we need to fill them up so we can
156
+# be sure the whole file is allocated. Do that by writing
157
+# consecutively smaller chunks starting from 8 MB, until the file
158
+# length increases even with a chunk size of 512. Then we must have
159
+# filled all holes.
160
+ofs=$((8 * 1024 * 1024))
161
+block_len=$((16 * 1024))
162
+while [[ $block_len -ge 512 ]]; do
163
+ file_len=$(stat -c '%s' "$TEST_IMG")
164
+ while [[ $(stat -c '%s' "$TEST_IMG") -eq $file_len ]]; do
165
+ # Do not include this in the reference output, it does not
166
+ # really matter which qemu-io calls we do here exactly
167
+ $QEMU_IO -c "write $ofs $block_len" "$TEST_IMG" >/dev/null
168
+ ofs=$((ofs + block_len))
169
+ done
170
+ block_len=$((block_len / 2))
171
+done
172
+
173
+# Fill up to 9M (do not include this in the reference output either,
174
+# $ofs is random for all we know)
175
+$QEMU_IO -c "write $ofs $((9 * 1024 * 1024 - ofs))" "$TEST_IMG" >/dev/null
176
+
177
+# Make space as follows:
178
+# - For the first refblock: Right at the beginning of the image (this
179
+# refblock is placed in the first place possible),
180
+# - For the reftable somewhere soon afterwards, still near the
181
+# beginning of the image (i.e. covered by the first refblock); the
182
+# reftable too is placed in the first place possible, but only after
183
+# all refblocks have been placed)
184
+# No space is needed for the other refblocks, because no refblock is
185
+# put before the space it covers. In this test case, we do not mind
186
+# if they are placed at the image file's end.
187
+
188
+# Before we make that space, we have to find out the host offset of
189
+# the area that belonged to the two data clusters at guest offset 4k,
190
+# because we expect the reftable to be placed there, and we will have
191
+# to verify that it is.
192
+
193
+l1_offset=$(peek_file_be "$TEST_IMG" 40 8)
194
+l2_offset=$(peek_file_be "$TEST_IMG" $l1_offset 8)
195
+l2_offset=$((l2_offset & 0x00fffffffffffe00))
196
+data_4k_offset=$(peek_file_be "$TEST_IMG" \
197
+ $((l2_offset + 4096 / 512 * 8)) 8)
198
+data_4k_offset=$((data_4k_offset & 0x00fffffffffffe00))
199
+
200
+$QEMU_IO -c "discard 0 512" -c "discard 4k 1k" "$TEST_IMG" | _filter_qemu_io
201
+
202
+# Corrupt the image by saying the image header was not allocated
203
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
204
+rb_offset=$(peek_file_be "$TEST_IMG" $rt_offset 8)
205
+poke_file "$TEST_IMG" $rb_offset "\x00\x00"
206
+
207
+echo
208
+# The only leaks there can be are the old refcount structures that are
209
+# leaked during rebuilding, no need to clutter the output with them
210
+_check_test_img -r all | grep -v '^Repairing cluster.*refcount=1 reference=0'
211
+echo
212
+
213
+# Check whether the reftable was put where we expected
214
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
215
+if [[ $rt_offset -eq $data_4k_offset ]]; then
216
+ echo 'OK: Reftable is where we expect it'
217
+else
218
+ echo "ERROR: Reftable is at $rt_offset, but was expected at $data_4k_offset"
219
+fi
220
+
221
+echo
222
+echo '--- Rebuilding refcount structures on block devices ---'
223
+echo
224
+
225
+# A block device cannot really grow, at least not during qemu-img
226
+# check. As mentioned in the above cases, rebuilding the refcount
227
+# structure may lead to new refcount structures being written after
228
+# the end of the image, and in the past that happened even if there
229
+# was more than sufficient space in the image. Such post-EOF writes
230
+# will not work on block devices, so test that the new algorithm
231
+# avoids it.
232
+
233
+# If we have passwordless sudo and losetup, we can use those to create
234
+# a block device. Otherwise, we can resort to qemu's FUSE export to
235
+# create a file that isn't growable, which effectively tests the same
236
+# thing.
237
+
238
+_cleanup_test_img
239
+truncate -s $((64 * 1024 * 1024)) "$TEST_IMG"
240
+
241
+if $loopdev; then
242
+ export_mp=$(sudo -n losetup --show -f "$TEST_IMG")
243
+ export_mp_driver=host_device
244
+ sudo -n chmod go+rw "$export_mp"
245
+else
246
+ # Create non-growable FUSE export that is a bit like an empty
247
+ # block device
248
+ export_mp="$TEST_DIR/fuse-export"
249
+ export_mp_driver=file
250
+ touch "$export_mp"
251
+
252
+ $QSD \
253
+ --blockdev file,node-name=export-node,filename="$TEST_IMG" \
254
+ --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off \
255
+ --pidfile "$TEST_DIR/qsd.pid" \
256
+ --daemonize
257
+fi
258
+
259
+# Now create a qcow2 image on the device -- unfortunately, qemu-img
260
+# create force-creates the file, so we have to resort to the
261
+# blockdev-create job.
262
+_launch_qemu \
263
+ --blockdev $export_mp_driver,node-name=file,filename="$export_mp"
264
+
265
+_send_qemu_cmd \
266
+ $QEMU_HANDLE \
267
+ '{ "execute": "qmp_capabilities" }' \
268
+ 'return'
269
+
270
+# Small cluster size again, so the image needs multiple refblocks
271
+_send_qemu_cmd \
272
+ $QEMU_HANDLE \
273
+ '{ "execute": "blockdev-create",
274
+ "arguments": {
275
+ "job-id": "create",
276
+ "options": {
277
+ "driver": "qcow2",
278
+ "file": "file",
279
+ "size": '$((64 * 1024 * 1024))',
280
+ "cluster-size": 512
281
+ } } }' \
282
+ '"concluded"'
283
+
284
+_send_qemu_cmd \
285
+ $QEMU_HANDLE \
286
+ '{ "execute": "job-dismiss", "arguments": { "id": "create" } }' \
287
+ 'return'
288
+
289
+_send_qemu_cmd \
290
+ $QEMU_HANDLE \
291
+ '{ "execute": "quit" }' \
292
+ 'return'
293
+
294
+wait=y _cleanup_qemu
295
+echo
296
+
297
+# Write some data
298
+$QEMU_IO -c 'write 0 64k' "$export_mp" | _filter_qemu_io
299
+
300
+# Corrupt the image by saying the image header was not allocated
301
+rt_offset=$(peek_file_be "$export_mp" 48 8)
302
+rb_offset=$(peek_file_be "$export_mp" $rt_offset 8)
303
+poke_file "$export_mp" $rb_offset "\x00\x00"
304
+
305
+# Repairing such a simple case should just work
306
+# (We used to put the reftable at the end of the image file, which can
307
+# never work for non-growable devices.)
308
+echo
309
+TEST_IMG="$export_mp" _check_test_img -r all \
310
+ | grep -v '^Repairing cluster.*refcount=1 reference=0'
311
+
312
+if $loopdev; then
313
+ sudo -n losetup -d "$export_mp"
314
+else
315
+ qsd_pid=$(cat "$TEST_DIR/qsd.pid")
316
+ kill -TERM "$qsd_pid"
317
+ # Wait for process to exit (cannot `wait` because the QSD is daemonized)
318
+ while [ -f "$TEST_DIR/qsd.pid" ]; do
319
+ true
320
+ done
321
+fi
322
+
323
# success, all done
324
echo '*** done'
325
rm -f $seq.full
326
diff --git a/tests/qemu-iotests/108.out b/tests/qemu-iotests/108.out
327
index XXXXXXX..XXXXXXX 100644
23
index XXXXXXX..XXXXXXX 100644
328
--- a/tests/qemu-iotests/108.out
24
--- a/block/vmdk.c
329
+++ b/tests/qemu-iotests/108.out
25
+++ b/block/vmdk.c
330
@@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired:
26
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
331
0 leaked clusters
27
error_setg(errp, "Invalid granularity, image may be corrupt");
332
1 corruptions
28
return -EFBIG;
333
29
}
334
+Double checking the fixed image now...
30
- if (l1_size > 512 * 1024 * 1024) {
335
+No errors were found on the image.
31
+ if (l1_size > 32 * 1024 * 1024) {
336
+
32
/*
337
+=== Check rebuilt reftable location ===
33
* Although with big capacity and small l1_entry_sectors, we can get a
338
+
34
* big l1_size, we don't want unbounded value to allocate the table.
339
+--- Does the image size increase? ---
35
- * Limit it to 512M, which is:
340
+
36
- * 16PB - for default "Hosted Sparse Extent" (VMDK4)
341
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
37
- * cluster size: 64KB, L2 table size: 512 entries
342
+wrote 65536/65536 bytes at offset 0
38
- * 1PB - for default "ESXi Host Sparse Extent" (VMDK3/vmfsSparse)
343
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
39
- * cluster size: 512B, L2 table size: 4096 entries
344
+
40
+ * Limit it to 32M, which is enough to store:
345
+ERROR cluster 0 refcount=0 reference=1
41
+ * 8TB - for both VMDK3 & VMDK4 with
346
+Rebuilding refcount structure
42
+ * minimal cluster size: 512B
347
+The following inconsistencies were found and repaired:
43
+ * minimal L2 table size: 512 entries
348
+
44
+ * 8 TB is still more than the maximal value supported for
349
+ 0 leaked clusters
45
+ * VMDK3 & VMDK4 which is 2TB.
350
+ 1 corruptions
46
*/
351
+
47
error_setg(errp, "L1 size too big");
352
+Double checking the fixed image now...
48
return -EFBIG;
353
+No errors were found on the image.
49
diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out
354
+
50
index XXXXXXX..XXXXXXX 100644
355
+OK: Image size did not change
51
--- a/tests/qemu-iotests/059.out
356
+
52
+++ b/tests/qemu-iotests/059.out
357
+--- Will the reftable occupy a hole specifically left for it? ---
53
@@ -XXX,XX +XXX,XX @@ Offset Length Mapped to File
358
+
54
0x140000000 0x10000 0x50000 TEST_DIR/t-s003.vmdk
359
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=9437184
55
360
+wrote 8388608/8388608 bytes at offset 0
56
=== Testing afl image with a very large capacity ===
361
+8 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
57
-qemu-img: Can't get image size 'TEST_DIR/afl9.IMGFMT': File too large
362
+discard 512/512 bytes at offset 0
58
+qemu-img: Could not open 'TEST_DIR/afl9.IMGFMT': L1 size too big
363
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
364
+discard 1024/1024 bytes at offset 4096
365
+1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
366
+
367
+ERROR cluster 0 refcount=0 reference=1
368
+Rebuilding refcount structure
369
+The following inconsistencies were found and repaired:
370
+
371
+ 0 leaked clusters
372
+ 1 corruptions
373
+
374
+Double checking the fixed image now...
375
+No errors were found on the image.
376
+
377
+OK: Reftable is where we expect it
378
+
379
+--- Rebuilding refcount structures on block devices ---
380
+
381
+{ "execute": "qmp_capabilities" }
382
+{"return": {}}
383
+{ "execute": "blockdev-create",
384
+ "arguments": {
385
+ "job-id": "create",
386
+ "options": {
387
+ "driver": "IMGFMT",
388
+ "file": "file",
389
+ "size": 67108864,
390
+ "cluster-size": 512
391
+ } } }
392
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "create"}}
393
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "create"}}
394
+{"return": {}}
395
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "create"}}
396
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "create"}}
397
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "create"}}
398
+{ "execute": "job-dismiss", "arguments": { "id": "create" } }
399
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "create"}}
400
+{"return": {}}
401
+{ "execute": "quit" }
402
+{"return": {}}
403
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}}
404
+
405
+wrote 65536/65536 bytes at offset 0
406
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
407
+
408
+ERROR cluster 0 refcount=0 reference=1
409
+Rebuilding refcount structure
410
+The following inconsistencies were found and repaired:
411
+
412
+ 0 leaked clusters
413
+ 1 corruptions
414
+
415
Double checking the fixed image now...
416
No errors were found on the image.
417
*** done
59
*** done
418
--
60
--
419
2.35.1
61
2.21.0
62
63
diff view generated by jsdifflib
1
From: Thomas Huth <thuth@redhat.com>
1
From: Sam Eiderman <shmuel.eiderman@oracle.com>
2
2
3
We want to get rid of check-block.sh in the long run, so let's move
3
Until ESXi 6.5 VMware used the vmfsSparse format for snapshots (VMDK3 in
4
the checks for the bash version and sanitizers from check-block.sh
4
QEMU).
5
into the meson.build file instead.
5
6
6
This format was lacking in the following:
7
Signed-off-by: Thomas Huth <thuth@redhat.com>
7
8
Message-Id: <20220223093840.2515281-4-thuth@redhat.com>
8
* Grain directory (L1) and grain table (L2) entries were 32-bit,
9
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
9
allowing access to only 2TB (slightly less) of data.
10
* The grain size (default) was 512 bytes - leading to data
11
fragmentation and many grain tables.
12
* For space reclamation purposes, it was necessary to find all the
13
grains which are not pointed to by any grain table - so a reverse
14
mapping of "offset of grain in vmdk" to "grain table" must be
15
constructed - which takes large amounts of CPU/RAM.
16
17
The format specification can be found in VMware's documentation:
18
https://www.vmware.com/support/developer/vddk/vmdk_50_technote.pdf
19
20
In ESXi 6.5, to support snapshot files larger than 2TB, a new format was
21
introduced: SESparse (Space Efficient).
22
23
This format fixes the above issues:
24
25
* All entries are now 64-bit.
26
* The grain size (default) is 4KB.
27
* Grain directory and grain tables are now located at the beginning
28
of the file.
29
+ seSparse format reserves space for all grain tables.
30
+ Grain tables can be addressed using an index.
31
+ Grains are located in the end of the file and can also be
32
addressed with an index.
33
- seSparse vmdks of large disks (64TB) have huge preallocated
34
headers - mainly due to L2 tables, even for empty snapshots.
35
* The header contains a reverse mapping ("backmap") of "offset of
36
grain in vmdk" to "grain table" and a bitmap ("free bitmap") which
37
specifies for each grain - whether it is allocated or not.
38
Using these data structures we can implement space reclamation
39
efficiently.
40
* Due to the fact that the header now maintains two mappings:
41
* The regular one (grain directory & grain tables)
42
* A reverse one (backmap and free bitmap)
43
These data structures can lose consistency upon crash and result
44
in a corrupted VMDK.
45
Therefore, a journal is also added to the VMDK and is replayed
46
when the VMware reopens the file after a crash.
47
48
Since ESXi 6.7 - SESparse is the only snapshot format available.
49
50
Unfortunately, VMware does not provide documentation regarding the new
51
seSparse format.
52
53
This commit is based on black-box research of the seSparse format.
54
Various in-guest block operations and their effect on the snapshot file
55
were tested.
56
57
The only VMware provided source of information (regarding the underlying
58
implementation) was a log file on the ESXi:
59
60
/var/log/hostd.log
61
62
Whenever an seSparse snapshot is created - the log is being populated
63
with seSparse records.
64
65
Relevant log records are of the form:
66
67
[...] Const Header:
68
[...] constMagic = 0xcafebabe
69
[...] version = 2.1
70
[...] capacity = 204800
71
[...] grainSize = 8
72
[...] grainTableSize = 64
73
[...] flags = 0
74
[...] Extents:
75
[...] Header : <1 : 1>
76
[...] JournalHdr : <2 : 2>
77
[...] Journal : <2048 : 2048>
78
[...] GrainDirectory : <4096 : 2048>
79
[...] GrainTables : <6144 : 2048>
80
[...] FreeBitmap : <8192 : 2048>
81
[...] BackMap : <10240 : 2048>
82
[...] Grain : <12288 : 204800>
83
[...] Volatile Header:
84
[...] volatileMagic = 0xcafecafe
85
[...] FreeGTNumber = 0
86
[...] nextTxnSeqNumber = 0
87
[...] replayJournal = 0
88
89
The sizes that are seen in the log file are in sectors.
90
Extents are of the following format: <offset : size>
91
92
This commit is a strict implementation which enforces:
93
* magics
94
* version number 2.1
95
* grain size of 8 sectors (4KB)
96
* grain table size of 64 sectors
97
* zero flags
98
* extent locations
99
100
Additionally, this commit proivdes only a subset of the functionality
101
offered by seSparse's format:
102
* Read-only
103
* No journal replay
104
* No space reclamation
105
* No unmap support
106
107
Hence, journal header, journal, free bitmap and backmap extents are
108
unused, only the "classic" (L1 -> L2 -> data) grain access is
109
implemented.
110
111
However there are several differences in the grain access itself.
112
Grain directory (L1):
113
* Grain directory entries are indexes (not offsets) to grain
114
tables.
115
* Valid grain directory entries have their highest nibble set to
116
0x1.
117
* Since grain tables are always located in the beginning of the
118
file - the index can fit into 32 bits - so we can use its low
119
part if it's valid.
120
Grain table (L2):
121
* Grain table entries are indexes (not offsets) to grains.
122
* If the highest nibble of the entry is:
123
0x0:
124
The grain in not allocated.
125
The rest of the bytes are 0.
126
0x1:
127
The grain is unmapped - guest sees a zero grain.
128
The rest of the bits point to the previously mapped grain,
129
see 0x3 case.
130
0x2:
131
The grain is zero.
132
0x3:
133
The grain is allocated - to get the index calculate:
134
((entry & 0x0fff000000000000) >> 48) |
135
((entry & 0x0000ffffffffffff) << 12)
136
* The difference between 0x1 and 0x2 is that 0x1 is an unallocated
137
grain which results from the guest using sg_unmap to unmap the
138
grain - but the grain itself still exists in the grain extent - a
139
space reclamation procedure should delete it.
140
Unmapping a zero grain has no effect (0x2 will not change to 0x1)
141
but unmapping an unallocated grain will (0x0 to 0x1) - naturally.
142
143
In order to implement seSparse some fields had to be changed to support
144
both 32-bit and 64-bit entry sizes.
145
146
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
147
Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com>
148
Reviewed-by: Arbel Moshe <arbel.moshe@oracle.com>
149
Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com>
150
Message-id: 20190620091057.47441-4-shmuel.eiderman@oracle.com
151
Signed-off-by: Max Reitz <mreitz@redhat.com>
10
---
152
---
11
tests/check-block.sh | 26 --------------------------
153
block/vmdk.c | 358 ++++++++++++++++++++++++++++++++++++++++++++++++---
12
tests/qemu-iotests/meson.build | 14 ++++++++++++++
154
1 file changed, 342 insertions(+), 16 deletions(-)
13
2 files changed, 14 insertions(+), 26 deletions(-)
155
14
156
diff --git a/block/vmdk.c b/block/vmdk.c
15
diff --git a/tests/check-block.sh b/tests/check-block.sh
157
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100755
158
--- a/block/vmdk.c
17
--- a/tests/check-block.sh
159
+++ b/block/vmdk.c
18
+++ b/tests/check-block.sh
160
@@ -XXX,XX +XXX,XX @@ typedef struct {
19
@@ -XXX,XX +XXX,XX @@ skip() {
161
uint16_t compressAlgorithm;
20
exit 0
162
} QEMU_PACKED VMDK4Header;
163
164
+typedef struct VMDKSESparseConstHeader {
165
+ uint64_t magic;
166
+ uint64_t version;
167
+ uint64_t capacity;
168
+ uint64_t grain_size;
169
+ uint64_t grain_table_size;
170
+ uint64_t flags;
171
+ uint64_t reserved1;
172
+ uint64_t reserved2;
173
+ uint64_t reserved3;
174
+ uint64_t reserved4;
175
+ uint64_t volatile_header_offset;
176
+ uint64_t volatile_header_size;
177
+ uint64_t journal_header_offset;
178
+ uint64_t journal_header_size;
179
+ uint64_t journal_offset;
180
+ uint64_t journal_size;
181
+ uint64_t grain_dir_offset;
182
+ uint64_t grain_dir_size;
183
+ uint64_t grain_tables_offset;
184
+ uint64_t grain_tables_size;
185
+ uint64_t free_bitmap_offset;
186
+ uint64_t free_bitmap_size;
187
+ uint64_t backmap_offset;
188
+ uint64_t backmap_size;
189
+ uint64_t grains_offset;
190
+ uint64_t grains_size;
191
+ uint8_t pad[304];
192
+} QEMU_PACKED VMDKSESparseConstHeader;
193
+
194
+typedef struct VMDKSESparseVolatileHeader {
195
+ uint64_t magic;
196
+ uint64_t free_gt_number;
197
+ uint64_t next_txn_seq_number;
198
+ uint64_t replay_journal;
199
+ uint8_t pad[480];
200
+} QEMU_PACKED VMDKSESparseVolatileHeader;
201
+
202
#define L2_CACHE_SIZE 16
203
204
typedef struct VmdkExtent {
205
@@ -XXX,XX +XXX,XX @@ typedef struct VmdkExtent {
206
bool compressed;
207
bool has_marker;
208
bool has_zero_grain;
209
+ bool sesparse;
210
+ uint64_t sesparse_l2_tables_offset;
211
+ uint64_t sesparse_clusters_offset;
212
+ int32_t entry_size;
213
int version;
214
int64_t sectors;
215
int64_t end_sector;
216
int64_t flat_start_offset;
217
int64_t l1_table_offset;
218
int64_t l1_backup_table_offset;
219
- uint32_t *l1_table;
220
+ void *l1_table;
221
uint32_t *l1_backup_table;
222
unsigned int l1_size;
223
uint32_t l1_entry_sectors;
224
225
unsigned int l2_size;
226
- uint32_t *l2_cache;
227
+ void *l2_cache;
228
uint32_t l2_cache_offsets[L2_CACHE_SIZE];
229
uint32_t l2_cache_counts[L2_CACHE_SIZE];
230
231
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
232
* minimal L2 table size: 512 entries
233
* 8 TB is still more than the maximal value supported for
234
* VMDK3 & VMDK4 which is 2TB.
235
+ * 64TB - for "ESXi seSparse Extent"
236
+ * minimal cluster size: 512B (default is 4KB)
237
+ * L2 table size: 4096 entries (const).
238
+ * 64TB is more than the maximal value supported for
239
+ * seSparse VMDKs (which is slightly less than 64TB)
240
*/
241
error_setg(errp, "L1 size too big");
242
return -EFBIG;
243
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
244
extent->l2_size = l2_size;
245
extent->cluster_sectors = flat ? sectors : cluster_sectors;
246
extent->next_cluster_sector = ROUND_UP(nb_sectors, cluster_sectors);
247
+ extent->entry_size = sizeof(uint32_t);
248
249
if (s->num_extents > 1) {
250
extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
251
@@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
252
int i;
253
254
/* read the L1 table */
255
- l1_size = extent->l1_size * sizeof(uint32_t);
256
+ l1_size = extent->l1_size * extent->entry_size;
257
extent->l1_table = g_try_malloc(l1_size);
258
if (l1_size && extent->l1_table == NULL) {
259
return -ENOMEM;
260
@@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
261
goto fail_l1;
262
}
263
for (i = 0; i < extent->l1_size; i++) {
264
- le32_to_cpus(&extent->l1_table[i]);
265
+ if (extent->entry_size == sizeof(uint64_t)) {
266
+ le64_to_cpus((uint64_t *)extent->l1_table + i);
267
+ } else {
268
+ assert(extent->entry_size == sizeof(uint32_t));
269
+ le32_to_cpus((uint32_t *)extent->l1_table + i);
270
+ }
271
}
272
273
if (extent->l1_backup_table_offset) {
274
+ assert(!extent->sesparse);
275
extent->l1_backup_table = g_try_malloc(l1_size);
276
if (l1_size && extent->l1_backup_table == NULL) {
277
ret = -ENOMEM;
278
@@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
279
}
280
281
extent->l2_cache =
282
- g_new(uint32_t, extent->l2_size * L2_CACHE_SIZE);
283
+ g_malloc(extent->entry_size * extent->l2_size * L2_CACHE_SIZE);
284
return 0;
285
fail_l1b:
286
g_free(extent->l1_backup_table);
287
@@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
288
return ret;
21
}
289
}
22
290
23
-# Disable tests with any sanitizer except for specific ones
291
+#define SESPARSE_CONST_HEADER_MAGIC UINT64_C(0x00000000cafebabe)
24
-SANITIZE_FLAGS=$( grep "CFLAGS.*-fsanitize" config-host.mak 2>/dev/null )
292
+#define SESPARSE_VOLATILE_HEADER_MAGIC UINT64_C(0x00000000cafecafe)
25
-ALLOWED_SANITIZE_FLAGS="safe-stack cfi-icall"
293
+
26
-#Remove all occurrencies of allowed Sanitize flags
294
+/* Strict checks - format not officially documented */
27
-for j in ${ALLOWED_SANITIZE_FLAGS}; do
295
+static int check_se_sparse_const_header(VMDKSESparseConstHeader *header,
28
- TMP_FLAGS=${SANITIZE_FLAGS}
296
+ Error **errp)
29
- SANITIZE_FLAGS=""
297
+{
30
- for i in ${TMP_FLAGS}; do
298
+ header->magic = le64_to_cpu(header->magic);
31
- if ! echo ${i} | grep -q "${j}" 2>/dev/null; then
299
+ header->version = le64_to_cpu(header->version);
32
- SANITIZE_FLAGS="${SANITIZE_FLAGS} ${i}"
300
+ header->grain_size = le64_to_cpu(header->grain_size);
33
- fi
301
+ header->grain_table_size = le64_to_cpu(header->grain_table_size);
34
- done
302
+ header->flags = le64_to_cpu(header->flags);
35
-done
303
+ header->reserved1 = le64_to_cpu(header->reserved1);
36
-if echo ${SANITIZE_FLAGS} | grep -q "\-fsanitize" 2>/dev/null; then
304
+ header->reserved2 = le64_to_cpu(header->reserved2);
37
- # Have a sanitize flag that is not allowed, stop
305
+ header->reserved3 = le64_to_cpu(header->reserved3);
38
- skip "Sanitizers are enabled ==> Not running the qemu-iotests."
306
+ header->reserved4 = le64_to_cpu(header->reserved4);
39
-fi
307
+
40
-
308
+ header->volatile_header_offset =
41
if [ -z "$(find . -name 'qemu-system-*' -print)" ]; then
309
+ le64_to_cpu(header->volatile_header_offset);
42
skip "No qemu-system binary available ==> Not running the qemu-iotests."
310
+ header->volatile_header_size = le64_to_cpu(header->volatile_header_size);
43
fi
311
+
44
312
+ header->journal_header_offset = le64_to_cpu(header->journal_header_offset);
45
-if ! command -v bash >/dev/null 2>&1 ; then
313
+ header->journal_header_size = le64_to_cpu(header->journal_header_size);
46
- skip "bash not available ==> Not running the qemu-iotests."
314
+
47
-fi
315
+ header->journal_offset = le64_to_cpu(header->journal_offset);
48
-
316
+ header->journal_size = le64_to_cpu(header->journal_size);
49
-if LANG=C bash --version | grep -q 'GNU bash, version [123]' ; then
317
+
50
- skip "bash version too old ==> Not running the qemu-iotests."
318
+ header->grain_dir_offset = le64_to_cpu(header->grain_dir_offset);
51
-fi
319
+ header->grain_dir_size = le64_to_cpu(header->grain_dir_size);
52
-
320
+
53
cd tests/qemu-iotests
321
+ header->grain_tables_offset = le64_to_cpu(header->grain_tables_offset);
54
322
+ header->grain_tables_size = le64_to_cpu(header->grain_tables_size);
55
# QEMU_CHECK_BLOCK_AUTO is used to disable some unstable sub-tests
323
+
56
diff --git a/tests/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build
324
+ header->free_bitmap_offset = le64_to_cpu(header->free_bitmap_offset);
57
index XXXXXXX..XXXXXXX 100644
325
+ header->free_bitmap_size = le64_to_cpu(header->free_bitmap_size);
58
--- a/tests/qemu-iotests/meson.build
326
+
59
+++ b/tests/qemu-iotests/meson.build
327
+ header->backmap_offset = le64_to_cpu(header->backmap_offset);
60
@@ -XXX,XX +XXX,XX @@ if not have_tools or targetos == 'windows' or get_option('gprof')
328
+ header->backmap_size = le64_to_cpu(header->backmap_size);
61
subdir_done()
329
+
62
endif
330
+ header->grains_offset = le64_to_cpu(header->grains_offset);
63
331
+ header->grains_size = le64_to_cpu(header->grains_size);
64
+foreach cflag: config_host['QEMU_CFLAGS'].split()
332
+
65
+ if cflag.startswith('-fsanitize') and \
333
+ if (header->magic != SESPARSE_CONST_HEADER_MAGIC) {
66
+ not cflag.contains('safe-stack') and not cflag.contains('cfi-icall')
334
+ error_setg(errp, "Bad const header magic: 0x%016" PRIx64,
67
+ message('Sanitizers are enabled ==> Disabled the qemu-iotests.')
335
+ header->magic);
68
+ subdir_done()
336
+ return -EINVAL;
69
+ endif
337
+ }
70
+endforeach
338
+
71
+
339
+ if (header->version != 0x0000000200000001) {
72
+bash = find_program('bash', required: false, version: '>= 4.0')
340
+ error_setg(errp, "Unsupported version: 0x%016" PRIx64,
73
+if not bash.found()
341
+ header->version);
74
+ message('bash >= v4.0 not available ==> Disabled the qemu-iotests.')
342
+ return -ENOTSUP;
75
+ subdir_done()
343
+ }
76
+endif
344
+
77
+
345
+ if (header->grain_size != 8) {
78
qemu_iotests_binaries = [qemu_img, qemu_io, qemu_nbd, qsd]
346
+ error_setg(errp, "Unsupported grain size: %" PRIu64,
79
qemu_iotests_env = {'PYTHON': python.full_path()}
347
+ header->grain_size);
80
qemu_iotests_formats = {
348
+ return -ENOTSUP;
349
+ }
350
+
351
+ if (header->grain_table_size != 64) {
352
+ error_setg(errp, "Unsupported grain table size: %" PRIu64,
353
+ header->grain_table_size);
354
+ return -ENOTSUP;
355
+ }
356
+
357
+ if (header->flags != 0) {
358
+ error_setg(errp, "Unsupported flags: 0x%016" PRIx64,
359
+ header->flags);
360
+ return -ENOTSUP;
361
+ }
362
+
363
+ if (header->reserved1 != 0 || header->reserved2 != 0 ||
364
+ header->reserved3 != 0 || header->reserved4 != 0) {
365
+ error_setg(errp, "Unsupported reserved bits:"
366
+ " 0x%016" PRIx64 " 0x%016" PRIx64
367
+ " 0x%016" PRIx64 " 0x%016" PRIx64,
368
+ header->reserved1, header->reserved2,
369
+ header->reserved3, header->reserved4);
370
+ return -ENOTSUP;
371
+ }
372
+
373
+ /* check that padding is 0 */
374
+ if (!buffer_is_zero(header->pad, sizeof(header->pad))) {
375
+ error_setg(errp, "Unsupported non-zero const header padding");
376
+ return -ENOTSUP;
377
+ }
378
+
379
+ return 0;
380
+}
381
+
382
+static int check_se_sparse_volatile_header(VMDKSESparseVolatileHeader *header,
383
+ Error **errp)
384
+{
385
+ header->magic = le64_to_cpu(header->magic);
386
+ header->free_gt_number = le64_to_cpu(header->free_gt_number);
387
+ header->next_txn_seq_number = le64_to_cpu(header->next_txn_seq_number);
388
+ header->replay_journal = le64_to_cpu(header->replay_journal);
389
+
390
+ if (header->magic != SESPARSE_VOLATILE_HEADER_MAGIC) {
391
+ error_setg(errp, "Bad volatile header magic: 0x%016" PRIx64,
392
+ header->magic);
393
+ return -EINVAL;
394
+ }
395
+
396
+ if (header->replay_journal) {
397
+ error_setg(errp, "Image is dirty, Replaying journal not supported");
398
+ return -ENOTSUP;
399
+ }
400
+
401
+ /* check that padding is 0 */
402
+ if (!buffer_is_zero(header->pad, sizeof(header->pad))) {
403
+ error_setg(errp, "Unsupported non-zero volatile header padding");
404
+ return -ENOTSUP;
405
+ }
406
+
407
+ return 0;
408
+}
409
+
410
+static int vmdk_open_se_sparse(BlockDriverState *bs,
411
+ BdrvChild *file,
412
+ int flags, Error **errp)
413
+{
414
+ int ret;
415
+ VMDKSESparseConstHeader const_header;
416
+ VMDKSESparseVolatileHeader volatile_header;
417
+ VmdkExtent *extent;
418
+
419
+ ret = bdrv_apply_auto_read_only(bs,
420
+ "No write support for seSparse images available", errp);
421
+ if (ret < 0) {
422
+ return ret;
423
+ }
424
+
425
+ assert(sizeof(const_header) == SECTOR_SIZE);
426
+
427
+ ret = bdrv_pread(file, 0, &const_header, sizeof(const_header));
428
+ if (ret < 0) {
429
+ bdrv_refresh_filename(file->bs);
430
+ error_setg_errno(errp, -ret,
431
+ "Could not read const header from file '%s'",
432
+ file->bs->filename);
433
+ return ret;
434
+ }
435
+
436
+ /* check const header */
437
+ ret = check_se_sparse_const_header(&const_header, errp);
438
+ if (ret < 0) {
439
+ return ret;
440
+ }
441
+
442
+ assert(sizeof(volatile_header) == SECTOR_SIZE);
443
+
444
+ ret = bdrv_pread(file,
445
+ const_header.volatile_header_offset * SECTOR_SIZE,
446
+ &volatile_header, sizeof(volatile_header));
447
+ if (ret < 0) {
448
+ bdrv_refresh_filename(file->bs);
449
+ error_setg_errno(errp, -ret,
450
+ "Could not read volatile header from file '%s'",
451
+ file->bs->filename);
452
+ return ret;
453
+ }
454
+
455
+ /* check volatile header */
456
+ ret = check_se_sparse_volatile_header(&volatile_header, errp);
457
+ if (ret < 0) {
458
+ return ret;
459
+ }
460
+
461
+ ret = vmdk_add_extent(bs, file, false,
462
+ const_header.capacity,
463
+ const_header.grain_dir_offset * SECTOR_SIZE,
464
+ 0,
465
+ const_header.grain_dir_size *
466
+ SECTOR_SIZE / sizeof(uint64_t),
467
+ const_header.grain_table_size *
468
+ SECTOR_SIZE / sizeof(uint64_t),
469
+ const_header.grain_size,
470
+ &extent,
471
+ errp);
472
+ if (ret < 0) {
473
+ return ret;
474
+ }
475
+
476
+ extent->sesparse = true;
477
+ extent->sesparse_l2_tables_offset = const_header.grain_tables_offset;
478
+ extent->sesparse_clusters_offset = const_header.grains_offset;
479
+ extent->entry_size = sizeof(uint64_t);
480
+
481
+ ret = vmdk_init_tables(bs, extent, errp);
482
+ if (ret) {
483
+ /* free extent allocated by vmdk_add_extent */
484
+ vmdk_free_last_extent(bs);
485
+ }
486
+
487
+ return ret;
488
+}
489
+
490
static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
491
QDict *options, Error **errp);
492
493
@@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
494
* RW [size in sectors] SPARSE "file-name.vmdk"
495
* RW [size in sectors] VMFS "file-name.vmdk"
496
* RW [size in sectors] VMFSSPARSE "file-name.vmdk"
497
+ * RW [size in sectors] SESPARSE "file-name.vmdk"
498
*/
499
flat_offset = -1;
500
matches = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
501
@@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
502
503
if (sectors <= 0 ||
504
(strcmp(type, "FLAT") && strcmp(type, "SPARSE") &&
505
- strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE")) ||
506
+ strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE") &&
507
+ strcmp(type, "SESPARSE")) ||
508
(strcmp(access, "RW"))) {
509
continue;
510
}
511
@@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
512
return ret;
513
}
514
extent = &s->extents[s->num_extents - 1];
515
+ } else if (!strcmp(type, "SESPARSE")) {
516
+ ret = vmdk_open_se_sparse(bs, extent_file, bs->open_flags, errp);
517
+ if (ret) {
518
+ bdrv_unref_child(bs, extent_file);
519
+ return ret;
520
+ }
521
+ extent = &s->extents[s->num_extents - 1];
522
} else {
523
error_setg(errp, "Unsupported extent type '%s'", type);
524
bdrv_unref_child(bs, extent_file);
525
@@ -XXX,XX +XXX,XX @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
526
if (strcmp(ct, "monolithicFlat") &&
527
strcmp(ct, "vmfs") &&
528
strcmp(ct, "vmfsSparse") &&
529
+ strcmp(ct, "seSparse") &&
530
strcmp(ct, "twoGbMaxExtentSparse") &&
531
strcmp(ct, "twoGbMaxExtentFlat")) {
532
error_setg(errp, "Unsupported image type '%s'", ct);
533
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
534
{
535
unsigned int l1_index, l2_offset, l2_index;
536
int min_index, i, j;
537
- uint32_t min_count, *l2_table;
538
+ uint32_t min_count;
539
+ void *l2_table;
540
bool zeroed = false;
541
int64_t ret;
542
int64_t cluster_sector;
543
+ unsigned int l2_size_bytes = extent->l2_size * extent->entry_size;
544
545
if (m_data) {
546
m_data->valid = 0;
547
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
548
if (l1_index >= extent->l1_size) {
549
return VMDK_ERROR;
550
}
551
- l2_offset = extent->l1_table[l1_index];
552
+ if (extent->sesparse) {
553
+ uint64_t l2_offset_u64;
554
+
555
+ assert(extent->entry_size == sizeof(uint64_t));
556
+
557
+ l2_offset_u64 = ((uint64_t *)extent->l1_table)[l1_index];
558
+ if (l2_offset_u64 == 0) {
559
+ l2_offset = 0;
560
+ } else if ((l2_offset_u64 & 0xffffffff00000000) != 0x1000000000000000) {
561
+ /*
562
+ * Top most nibble is 0x1 if grain table is allocated.
563
+ * strict check - top most 4 bytes must be 0x10000000 since max
564
+ * supported size is 64TB for disk - so no more than 64TB / 16MB
565
+ * grain directories which is smaller than uint32,
566
+ * where 16MB is the only supported default grain table coverage.
567
+ */
568
+ return VMDK_ERROR;
569
+ } else {
570
+ l2_offset_u64 = l2_offset_u64 & 0x00000000ffffffff;
571
+ l2_offset_u64 = extent->sesparse_l2_tables_offset +
572
+ l2_offset_u64 * l2_size_bytes / SECTOR_SIZE;
573
+ if (l2_offset_u64 > 0x00000000ffffffff) {
574
+ return VMDK_ERROR;
575
+ }
576
+ l2_offset = (unsigned int)(l2_offset_u64);
577
+ }
578
+ } else {
579
+ assert(extent->entry_size == sizeof(uint32_t));
580
+ l2_offset = ((uint32_t *)extent->l1_table)[l1_index];
581
+ }
582
if (!l2_offset) {
583
return VMDK_UNALLOC;
584
}
585
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
586
extent->l2_cache_counts[j] >>= 1;
587
}
588
}
589
- l2_table = extent->l2_cache + (i * extent->l2_size);
590
+ l2_table = (char *)extent->l2_cache + (i * l2_size_bytes);
591
goto found;
592
}
593
}
594
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
595
min_index = i;
596
}
597
}
598
- l2_table = extent->l2_cache + (min_index * extent->l2_size);
599
+ l2_table = (char *)extent->l2_cache + (min_index * l2_size_bytes);
600
BLKDBG_EVENT(extent->file, BLKDBG_L2_LOAD);
601
if (bdrv_pread(extent->file,
602
(int64_t)l2_offset * 512,
603
l2_table,
604
- extent->l2_size * sizeof(uint32_t)
605
- ) != extent->l2_size * sizeof(uint32_t)) {
606
+ l2_size_bytes
607
+ ) != l2_size_bytes) {
608
return VMDK_ERROR;
609
}
610
611
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
612
extent->l2_cache_counts[min_index] = 1;
613
found:
614
l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size;
615
- cluster_sector = le32_to_cpu(l2_table[l2_index]);
616
617
- if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
618
- zeroed = true;
619
+ if (extent->sesparse) {
620
+ cluster_sector = le64_to_cpu(((uint64_t *)l2_table)[l2_index]);
621
+ switch (cluster_sector & 0xf000000000000000) {
622
+ case 0x0000000000000000:
623
+ /* unallocated grain */
624
+ if (cluster_sector != 0) {
625
+ return VMDK_ERROR;
626
+ }
627
+ break;
628
+ case 0x1000000000000000:
629
+ /* scsi-unmapped grain - fallthrough */
630
+ case 0x2000000000000000:
631
+ /* zero grain */
632
+ zeroed = true;
633
+ break;
634
+ case 0x3000000000000000:
635
+ /* allocated grain */
636
+ cluster_sector = (((cluster_sector & 0x0fff000000000000) >> 48) |
637
+ ((cluster_sector & 0x0000ffffffffffff) << 12));
638
+ cluster_sector = extent->sesparse_clusters_offset +
639
+ cluster_sector * extent->cluster_sectors;
640
+ break;
641
+ default:
642
+ return VMDK_ERROR;
643
+ }
644
+ } else {
645
+ cluster_sector = le32_to_cpu(((uint32_t *)l2_table)[l2_index]);
646
+
647
+ if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
648
+ zeroed = true;
649
+ }
650
}
651
652
if (!cluster_sector || zeroed) {
653
if (!allocate) {
654
return zeroed ? VMDK_ZEROED : VMDK_UNALLOC;
655
}
656
+ assert(!extent->sesparse);
657
658
if (extent->next_cluster_sector >= VMDK_EXTENT_MAX_SECTORS) {
659
return VMDK_ERROR;
660
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
661
m_data->l1_index = l1_index;
662
m_data->l2_index = l2_index;
663
m_data->l2_offset = l2_offset;
664
- m_data->l2_cache_entry = &l2_table[l2_index];
665
+ m_data->l2_cache_entry = ((uint32_t *)l2_table) + l2_index;
666
}
667
}
668
*cluster_offset = cluster_sector << BDRV_SECTOR_BITS;
669
@@ -XXX,XX +XXX,XX @@ static int vmdk_pwritev(BlockDriverState *bs, uint64_t offset,
670
if (!extent) {
671
return -EIO;
672
}
673
+ if (extent->sesparse) {
674
+ return -ENOTSUP;
675
+ }
676
offset_in_cluster = vmdk_find_offset_in_cluster(extent, offset);
677
n_bytes = MIN(bytes, extent->cluster_sectors * BDRV_SECTOR_SIZE
678
- offset_in_cluster);
81
--
679
--
82
2.35.1
680
2.21.0
681
682
diff view generated by jsdifflib
1
When rebuilding the refcount structures (when qemu-img check -r found
1
From: Pino Toscano <ptoscano@redhat.com>
2
errors with refcount = 0, but reference count > 0), the new refcount
3
table defaults to being put at the image file end[1]. There is no good
4
reason for that except that it means we will not have to rewrite any
5
refblocks we already wrote to disk.
6
2
7
Changing the code to rewrite those refblocks is not too difficult,
3
Rewrite the implementation of the ssh block driver to use libssh instead
8
though, so let us do that. That is beneficial for images on block
4
of libssh2. The libssh library has various advantages over libssh2:
9
devices, where we cannot really write beyond the end of the image file.
5
- easier API for authentication (for example for using ssh-agent)
6
- easier API for known_hosts handling
7
- supports newer types of keys in known_hosts
10
8
11
Use this opportunity to add extensive comments to the code, and refactor
9
Use APIs/features available in libssh 0.8 conditionally, to support
12
it a bit, getting rid of the backwards-jumping goto.
10
older versions (which are not recommended though).
13
11
14
[1] Unless there is something allocated in the area pointed to by the
12
Adjust the iotest 207 according to the different error message, and to
15
last refblock, so we have to write that refblock. In that case, we
13
find the default key type for localhost (to properly compare the
16
try to put the reftable in there.
14
fingerprint with).
15
Contributed-by: Max Reitz <mreitz@redhat.com>
17
16
18
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1519071
17
Adjust the various Docker/Travis scripts to use libssh when available
19
Closes: https://gitlab.com/qemu-project/qemu/-/issues/941
18
instead of libssh2. The mingw/mxe testing is dropped for now, as there
20
Reviewed-by: Eric Blake <eblake@redhat.com>
19
are no packages for it.
21
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
20
22
Message-Id: <20220405134652.19278-2-hreitz@redhat.com>
21
Signed-off-by: Pino Toscano <ptoscano@redhat.com>
22
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
23
Acked-by: Alex Bennée <alex.bennee@linaro.org>
24
Message-id: 20190620200840.17655-1-ptoscano@redhat.com
25
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
26
Message-id: 5873173.t2JhDm7DL7@lindworm.usersys.redhat.com
27
Signed-off-by: Max Reitz <mreitz@redhat.com>
23
---
28
---
24
block/qcow2-refcount.c | 332 +++++++++++++++++++++++++++++------------
29
configure | 65 +-
25
1 file changed, 235 insertions(+), 97 deletions(-)
30
block/Makefile.objs | 6 +-
31
block/ssh.c | 652 ++++++++++--------
32
.travis.yml | 4 +-
33
block/trace-events | 14 +-
34
docs/qemu-block-drivers.texi | 2 +-
35
.../dockerfiles/debian-win32-cross.docker | 1 -
36
.../dockerfiles/debian-win64-cross.docker | 1 -
37
tests/docker/dockerfiles/fedora.docker | 4 +-
38
tests/docker/dockerfiles/ubuntu.docker | 2 +-
39
tests/docker/dockerfiles/ubuntu1804.docker | 2 +-
40
tests/qemu-iotests/207 | 54 +-
41
tests/qemu-iotests/207.out | 2 +-
42
13 files changed, 449 insertions(+), 360 deletions(-)
26
43
27
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
44
diff --git a/configure b/configure
45
index XXXXXXX..XXXXXXX 100755
46
--- a/configure
47
+++ b/configure
48
@@ -XXX,XX +XXX,XX @@ auth_pam=""
49
vte=""
50
virglrenderer=""
51
tpm=""
52
-libssh2=""
53
+libssh=""
54
live_block_migration="yes"
55
numa=""
56
tcmalloc="no"
57
@@ -XXX,XX +XXX,XX @@ for opt do
58
;;
59
--enable-tpm) tpm="yes"
60
;;
61
- --disable-libssh2) libssh2="no"
62
+ --disable-libssh) libssh="no"
63
;;
64
- --enable-libssh2) libssh2="yes"
65
+ --enable-libssh) libssh="yes"
66
;;
67
--disable-live-block-migration) live_block_migration="no"
68
;;
69
@@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available:
70
coroutine-pool coroutine freelist (better performance)
71
glusterfs GlusterFS backend
72
tpm TPM support
73
- libssh2 ssh block device support
74
+ libssh ssh block device support
75
numa libnuma support
76
libxml2 for Parallels image format
77
tcmalloc tcmalloc support
78
@@ -XXX,XX +XXX,XX @@ EOF
79
fi
80
81
##########################################
82
-# libssh2 probe
83
-min_libssh2_version=1.2.8
84
-if test "$libssh2" != "no" ; then
85
- if $pkg_config --atleast-version=$min_libssh2_version libssh2; then
86
- libssh2_cflags=$($pkg_config libssh2 --cflags)
87
- libssh2_libs=$($pkg_config libssh2 --libs)
88
- libssh2=yes
89
+# libssh probe
90
+if test "$libssh" != "no" ; then
91
+ if $pkg_config --exists libssh; then
92
+ libssh_cflags=$($pkg_config libssh --cflags)
93
+ libssh_libs=$($pkg_config libssh --libs)
94
+ libssh=yes
95
else
96
- if test "$libssh2" = "yes" ; then
97
- error_exit "libssh2 >= $min_libssh2_version required for --enable-libssh2"
98
+ if test "$libssh" = "yes" ; then
99
+ error_exit "libssh required for --enable-libssh"
100
fi
101
- libssh2=no
102
+ libssh=no
103
fi
104
fi
105
106
##########################################
107
-# libssh2_sftp_fsync probe
108
+# Check for libssh 0.8
109
+# This is done like this instead of using the LIBSSH_VERSION_* and
110
+# SSH_VERSION_* macros because some distributions in the past shipped
111
+# snapshots of the future 0.8 from Git, and those snapshots did not
112
+# have updated version numbers (still referring to 0.7.0).
113
114
-if test "$libssh2" = "yes"; then
115
+if test "$libssh" = "yes"; then
116
cat > $TMPC <<EOF
117
-#include <stdio.h>
118
-#include <libssh2.h>
119
-#include <libssh2_sftp.h>
120
-int main(void) {
121
- LIBSSH2_SESSION *session;
122
- LIBSSH2_SFTP *sftp;
123
- LIBSSH2_SFTP_HANDLE *sftp_handle;
124
- session = libssh2_session_init ();
125
- sftp = libssh2_sftp_init (session);
126
- sftp_handle = libssh2_sftp_open (sftp, "/", 0, 0);
127
- libssh2_sftp_fsync (sftp_handle);
128
- return 0;
129
-}
130
+#include <libssh/libssh.h>
131
+int main(void) { return ssh_get_server_publickey(NULL, NULL); }
132
EOF
133
- # libssh2_cflags/libssh2_libs defined in previous test.
134
- if compile_prog "$libssh2_cflags" "$libssh2_libs" ; then
135
- QEMU_CFLAGS="-DHAS_LIBSSH2_SFTP_FSYNC $QEMU_CFLAGS"
136
+ if compile_prog "$libssh_cflags" "$libssh_libs"; then
137
+ libssh_cflags="-DHAVE_LIBSSH_0_8 $libssh_cflags"
138
fi
139
fi
140
141
@@ -XXX,XX +XXX,XX @@ echo "GlusterFS support $glusterfs"
142
echo "gcov $gcov_tool"
143
echo "gcov enabled $gcov"
144
echo "TPM support $tpm"
145
-echo "libssh2 support $libssh2"
146
+echo "libssh support $libssh"
147
echo "QOM debugging $qom_cast_debug"
148
echo "Live block migration $live_block_migration"
149
echo "lzo support $lzo"
150
@@ -XXX,XX +XXX,XX @@ if test "$glusterfs_iocb_has_stat" = "yes" ; then
151
echo "CONFIG_GLUSTERFS_IOCB_HAS_STAT=y" >> $config_host_mak
152
fi
153
154
-if test "$libssh2" = "yes" ; then
155
- echo "CONFIG_LIBSSH2=m" >> $config_host_mak
156
- echo "LIBSSH2_CFLAGS=$libssh2_cflags" >> $config_host_mak
157
- echo "LIBSSH2_LIBS=$libssh2_libs" >> $config_host_mak
158
+if test "$libssh" = "yes" ; then
159
+ echo "CONFIG_LIBSSH=m" >> $config_host_mak
160
+ echo "LIBSSH_CFLAGS=$libssh_cflags" >> $config_host_mak
161
+ echo "LIBSSH_LIBS=$libssh_libs" >> $config_host_mak
162
fi
163
164
if test "$live_block_migration" = "yes" ; then
165
diff --git a/block/Makefile.objs b/block/Makefile.objs
28
index XXXXXXX..XXXXXXX 100644
166
index XXXXXXX..XXXXXXX 100644
29
--- a/block/qcow2-refcount.c
167
--- a/block/Makefile.objs
30
+++ b/block/qcow2-refcount.c
168
+++ b/block/Makefile.objs
31
@@ -XXX,XX +XXX,XX @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs,
169
@@ -XXX,XX +XXX,XX @@ block-obj-$(CONFIG_CURL) += curl.o
170
block-obj-$(CONFIG_RBD) += rbd.o
171
block-obj-$(CONFIG_GLUSTERFS) += gluster.o
172
block-obj-$(CONFIG_VXHS) += vxhs.o
173
-block-obj-$(CONFIG_LIBSSH2) += ssh.o
174
+block-obj-$(CONFIG_LIBSSH) += ssh.o
175
block-obj-y += accounting.o dirty-bitmap.o
176
block-obj-y += write-threshold.o
177
block-obj-y += backup.o
178
@@ -XXX,XX +XXX,XX @@ rbd.o-libs := $(RBD_LIBS)
179
gluster.o-cflags := $(GLUSTERFS_CFLAGS)
180
gluster.o-libs := $(GLUSTERFS_LIBS)
181
vxhs.o-libs := $(VXHS_LIBS)
182
-ssh.o-cflags := $(LIBSSH2_CFLAGS)
183
-ssh.o-libs := $(LIBSSH2_LIBS)
184
+ssh.o-cflags := $(LIBSSH_CFLAGS)
185
+ssh.o-libs := $(LIBSSH_LIBS)
186
block-obj-dmg-bz2-$(CONFIG_BZIP2) += dmg-bz2.o
187
block-obj-$(if $(CONFIG_DMG),m,n) += $(block-obj-dmg-bz2-y)
188
dmg-bz2.o-libs := $(BZIP2_LIBS)
189
diff --git a/block/ssh.c b/block/ssh.c
190
index XXXXXXX..XXXXXXX 100644
191
--- a/block/ssh.c
192
+++ b/block/ssh.c
193
@@ -XXX,XX +XXX,XX @@
194
195
#include "qemu/osdep.h"
196
197
-#include <libssh2.h>
198
-#include <libssh2_sftp.h>
199
+#include <libssh/libssh.h>
200
+#include <libssh/sftp.h>
201
202
#include "block/block_int.h"
203
#include "block/qdict.h"
204
@@ -XXX,XX +XXX,XX @@
205
#include "trace.h"
206
207
/*
208
- * TRACE_LIBSSH2=<bitmask> enables tracing in libssh2 itself. Note
209
- * that this requires that libssh2 was specially compiled with the
210
- * `./configure --enable-debug' option, so most likely you will have
211
- * to compile it yourself. The meaning of <bitmask> is described
212
- * here: http://www.libssh2.org/libssh2_trace.html
213
+ * TRACE_LIBSSH=<level> enables tracing in libssh itself.
214
+ * The meaning of <level> is described here:
215
+ * http://api.libssh.org/master/group__libssh__log.html
216
*/
217
-#define TRACE_LIBSSH2 0 /* or try: LIBSSH2_TRACE_SFTP */
218
+#define TRACE_LIBSSH 0 /* see: SSH_LOG_* */
219
220
typedef struct BDRVSSHState {
221
/* Coroutine. */
222
@@ -XXX,XX +XXX,XX @@ typedef struct BDRVSSHState {
223
224
/* SSH connection. */
225
int sock; /* socket */
226
- LIBSSH2_SESSION *session; /* ssh session */
227
- LIBSSH2_SFTP *sftp; /* sftp session */
228
- LIBSSH2_SFTP_HANDLE *sftp_handle; /* sftp remote file handle */
229
+ ssh_session session; /* ssh session */
230
+ sftp_session sftp; /* sftp session */
231
+ sftp_file sftp_handle; /* sftp remote file handle */
232
233
- /* See ssh_seek() function below. */
234
- int64_t offset;
235
- bool offset_op_read;
236
-
237
- /* File attributes at open. We try to keep the .filesize field
238
+ /*
239
+ * File attributes at open. We try to keep the .size field
240
* updated if it changes (eg by writing at the end of the file).
241
*/
242
- LIBSSH2_SFTP_ATTRIBUTES attrs;
243
+ sftp_attributes attrs;
244
245
InetSocketAddress *inet;
246
247
@@ -XXX,XX +XXX,XX @@ static void ssh_state_init(BDRVSSHState *s)
248
{
249
memset(s, 0, sizeof *s);
250
s->sock = -1;
251
- s->offset = -1;
252
qemu_co_mutex_init(&s->lock);
32
}
253
}
33
254
34
/*
255
@@ -XXX,XX +XXX,XX @@ static void ssh_state_free(BDRVSSHState *s)
35
- * Creates a new refcount structure based solely on the in-memory information
36
- * given through *refcount_table. All necessary allocations will be reflected
37
- * in that array.
38
+ * Helper function for rebuild_refcount_structure().
39
*
40
- * On success, the old refcount structure is leaked (it will be covered by the
41
- * new refcount structure).
42
+ * Scan the range of clusters [first_cluster, end_cluster) for allocated
43
+ * clusters and write all corresponding refblocks to disk. The refblock
44
+ * and allocation data is taken from the in-memory refcount table
45
+ * *refcount_table[] (of size *nb_clusters), which is basically one big
46
+ * (unlimited size) refblock for the whole image.
47
+ *
48
+ * For these refblocks, clusters are allocated using said in-memory
49
+ * refcount table. Care is taken that these allocations are reflected
50
+ * in the refblocks written to disk.
51
+ *
52
+ * The refblocks' offsets are written into a reftable, which is
53
+ * *on_disk_reftable_ptr[] (of size *on_disk_reftable_entries_ptr). If
54
+ * that reftable is of insufficient size, it will be resized to fit.
55
+ * This reftable is not written to disk.
56
+ *
57
+ * (If *on_disk_reftable_ptr is not NULL, the entries within are assumed
58
+ * to point to existing valid refblocks that do not need to be allocated
59
+ * again.)
60
+ *
61
+ * Return whether the on-disk reftable array was resized (true/false),
62
+ * or -errno on error.
63
*/
64
-static int rebuild_refcount_structure(BlockDriverState *bs,
65
- BdrvCheckResult *res,
66
- void **refcount_table,
67
- int64_t *nb_clusters)
68
+static int rebuild_refcounts_write_refblocks(
69
+ BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters,
70
+ int64_t first_cluster, int64_t end_cluster,
71
+ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr
72
+ )
73
{
256
{
74
BDRVQcow2State *s = bs->opaque;
257
g_free(s->user);
75
- int64_t first_free_cluster = 0, reftable_offset = -1, cluster = 0;
258
76
+ int64_t cluster;
259
+ if (s->attrs) {
77
int64_t refblock_offset, refblock_start, refblock_index;
260
+ sftp_attributes_free(s->attrs);
78
- uint32_t reftable_size = 0;
261
+ }
79
- uint64_t *on_disk_reftable = NULL;
262
if (s->sftp_handle) {
80
+ int64_t first_free_cluster = 0;
263
- libssh2_sftp_close(s->sftp_handle);
81
+ uint64_t *on_disk_reftable = *on_disk_reftable_ptr;
264
+ sftp_close(s->sftp_handle);
82
+ uint32_t on_disk_reftable_entries = *on_disk_reftable_entries_ptr;
265
}
83
void *on_disk_refblock;
266
if (s->sftp) {
84
- int ret = 0;
267
- libssh2_sftp_shutdown(s->sftp);
85
- struct {
268
+ sftp_free(s->sftp);
86
- uint64_t reftable_offset;
269
}
87
- uint32_t reftable_clusters;
270
if (s->session) {
88
- } QEMU_PACKED reftable_offset_and_clusters;
271
- libssh2_session_disconnect(s->session,
272
- "from qemu ssh client: "
273
- "user closed the connection");
274
- libssh2_session_free(s->session);
275
- }
276
- if (s->sock >= 0) {
277
- close(s->sock);
278
+ ssh_disconnect(s->session);
279
+ ssh_free(s->session); /* This frees s->sock */
280
}
281
}
282
283
@@ -XXX,XX +XXX,XX @@ session_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
284
va_end(args);
285
286
if (s->session) {
287
- char *ssh_err;
288
+ const char *ssh_err;
289
int ssh_err_code;
290
291
- /* This is not an errno. See <libssh2.h>. */
292
- ssh_err_code = libssh2_session_last_error(s->session,
293
- &ssh_err, NULL, 0);
294
- error_setg(errp, "%s: %s (libssh2 error code: %d)",
295
+ /* This is not an errno. See <libssh/libssh.h>. */
296
+ ssh_err = ssh_get_error(s->session);
297
+ ssh_err_code = ssh_get_error_code(s->session);
298
+ error_setg(errp, "%s: %s (libssh error code: %d)",
299
msg, ssh_err, ssh_err_code);
300
} else {
301
error_setg(errp, "%s", msg);
302
@@ -XXX,XX +XXX,XX @@ sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
303
va_end(args);
304
305
if (s->sftp) {
306
- char *ssh_err;
307
+ const char *ssh_err;
308
int ssh_err_code;
309
- unsigned long sftp_err_code;
310
+ int sftp_err_code;
311
312
- /* This is not an errno. See <libssh2.h>. */
313
- ssh_err_code = libssh2_session_last_error(s->session,
314
- &ssh_err, NULL, 0);
315
- /* See <libssh2_sftp.h>. */
316
- sftp_err_code = libssh2_sftp_last_error((s)->sftp);
317
+ /* This is not an errno. See <libssh/libssh.h>. */
318
+ ssh_err = ssh_get_error(s->session);
319
+ ssh_err_code = ssh_get_error_code(s->session);
320
+ /* See <libssh/sftp.h>. */
321
+ sftp_err_code = sftp_get_error(s->sftp);
322
323
error_setg(errp,
324
- "%s: %s (libssh2 error code: %d, sftp error code: %lu)",
325
+ "%s: %s (libssh error code: %d, sftp error code: %d)",
326
msg, ssh_err, ssh_err_code, sftp_err_code);
327
} else {
328
error_setg(errp, "%s", msg);
329
@@ -XXX,XX +XXX,XX @@ sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
330
331
static void sftp_error_trace(BDRVSSHState *s, const char *op)
332
{
333
- char *ssh_err;
334
+ const char *ssh_err;
335
int ssh_err_code;
336
- unsigned long sftp_err_code;
337
+ int sftp_err_code;
338
339
- /* This is not an errno. See <libssh2.h>. */
340
- ssh_err_code = libssh2_session_last_error(s->session,
341
- &ssh_err, NULL, 0);
342
- /* See <libssh2_sftp.h>. */
343
- sftp_err_code = libssh2_sftp_last_error((s)->sftp);
344
+ /* This is not an errno. See <libssh/libssh.h>. */
345
+ ssh_err = ssh_get_error(s->session);
346
+ ssh_err_code = ssh_get_error_code(s->session);
347
+ /* See <libssh/sftp.h>. */
348
+ sftp_err_code = sftp_get_error(s->sftp);
349
350
trace_sftp_error(op, ssh_err, ssh_err_code, sftp_err_code);
351
}
352
@@ -XXX,XX +XXX,XX @@ static void ssh_parse_filename(const char *filename, QDict *options,
353
parse_uri(filename, options, errp);
354
}
355
356
-static int check_host_key_knownhosts(BDRVSSHState *s,
357
- const char *host, int port, Error **errp)
358
+static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp)
359
{
360
- const char *home;
361
- char *knh_file = NULL;
362
- LIBSSH2_KNOWNHOSTS *knh = NULL;
363
- struct libssh2_knownhost *found;
364
- int ret, r;
365
- const char *hostkey;
366
- size_t len;
367
- int type;
89
-
368
-
90
- qcow2_cache_empty(bs, s->refcount_block_cache);
369
- hostkey = libssh2_session_hostkey(s->session, &len, &type);
91
+ bool reftable_grown = false;
370
- if (!hostkey) {
92
+ int ret;
371
+ int ret;
93
372
+#ifdef HAVE_LIBSSH_0_8
94
-write_refblocks:
373
+ enum ssh_known_hosts_e state;
95
- for (; cluster < *nb_clusters; cluster++) {
374
+ int r;
96
+ for (cluster = first_cluster; cluster < end_cluster; cluster++) {
375
+ ssh_key pubkey;
97
+ /* Check all clusters to find refblocks that contain non-zero entries */
376
+ enum ssh_keytypes_e pubkey_type;
98
if (!s->get_refcount(*refcount_table, cluster)) {
377
+ unsigned char *server_hash = NULL;
99
continue;
378
+ size_t server_hash_len;
379
+ char *fingerprint = NULL;
380
+
381
+ state = ssh_session_is_known_server(s->session);
382
+ trace_ssh_server_status(state);
383
+
384
+ switch (state) {
385
+ case SSH_KNOWN_HOSTS_OK:
386
+ /* OK */
387
+ trace_ssh_check_host_key_knownhosts();
388
+ break;
389
+ case SSH_KNOWN_HOSTS_CHANGED:
390
ret = -EINVAL;
391
- session_error_setg(errp, s, "failed to read remote host key");
392
+ r = ssh_get_server_publickey(s->session, &pubkey);
393
+ if (r == 0) {
394
+ r = ssh_get_publickey_hash(pubkey, SSH_PUBLICKEY_HASH_SHA256,
395
+ &server_hash, &server_hash_len);
396
+ pubkey_type = ssh_key_type(pubkey);
397
+ ssh_key_free(pubkey);
398
+ }
399
+ if (r == 0) {
400
+ fingerprint = ssh_get_fingerprint_hash(SSH_PUBLICKEY_HASH_SHA256,
401
+ server_hash,
402
+ server_hash_len);
403
+ ssh_clean_pubkey_hash(&server_hash);
404
+ }
405
+ if (fingerprint) {
406
+ error_setg(errp,
407
+ "host key (%s key with fingerprint %s) does not match "
408
+ "the one in known_hosts; this may be a possible attack",
409
+ ssh_key_type_to_char(pubkey_type), fingerprint);
410
+ ssh_string_free_char(fingerprint);
411
+ } else {
412
+ error_setg(errp,
413
+ "host key does not match the one in known_hosts; this "
414
+ "may be a possible attack");
415
+ }
416
goto out;
417
- }
418
-
419
- knh = libssh2_knownhost_init(s->session);
420
- if (!knh) {
421
+ case SSH_KNOWN_HOSTS_OTHER:
422
ret = -EINVAL;
423
- session_error_setg(errp, s,
424
- "failed to initialize known hosts support");
425
+ error_setg(errp,
426
+ "host key for this server not found, another type exists");
427
+ goto out;
428
+ case SSH_KNOWN_HOSTS_UNKNOWN:
429
+ ret = -EINVAL;
430
+ error_setg(errp, "no host key was found in known_hosts");
431
+ goto out;
432
+ case SSH_KNOWN_HOSTS_NOT_FOUND:
433
+ ret = -ENOENT;
434
+ error_setg(errp, "known_hosts file not found");
435
+ goto out;
436
+ case SSH_KNOWN_HOSTS_ERROR:
437
+ ret = -EINVAL;
438
+ error_setg(errp, "error while checking the host");
439
+ goto out;
440
+ default:
441
+ ret = -EINVAL;
442
+ error_setg(errp, "error while checking for known server (%d)", state);
443
goto out;
444
}
445
+#else /* !HAVE_LIBSSH_0_8 */
446
+ int state;
447
448
- home = getenv("HOME");
449
- if (home) {
450
- knh_file = g_strdup_printf("%s/.ssh/known_hosts", home);
451
- } else {
452
- knh_file = g_strdup_printf("/root/.ssh/known_hosts");
453
- }
454
-
455
- /* Read all known hosts from OpenSSH-style known_hosts file. */
456
- libssh2_knownhost_readfile(knh, knh_file, LIBSSH2_KNOWNHOST_FILE_OPENSSH);
457
+ state = ssh_is_server_known(s->session);
458
+ trace_ssh_server_status(state);
459
460
- r = libssh2_knownhost_checkp(knh, host, port, hostkey, len,
461
- LIBSSH2_KNOWNHOST_TYPE_PLAIN|
462
- LIBSSH2_KNOWNHOST_KEYENC_RAW,
463
- &found);
464
- switch (r) {
465
- case LIBSSH2_KNOWNHOST_CHECK_MATCH:
466
+ switch (state) {
467
+ case SSH_SERVER_KNOWN_OK:
468
/* OK */
469
- trace_ssh_check_host_key_knownhosts(found->key);
470
+ trace_ssh_check_host_key_knownhosts();
471
break;
472
- case LIBSSH2_KNOWNHOST_CHECK_MISMATCH:
473
+ case SSH_SERVER_KNOWN_CHANGED:
474
ret = -EINVAL;
475
- session_error_setg(errp, s,
476
- "host key does not match the one in known_hosts"
477
- " (found key %s)", found->key);
478
+ error_setg(errp,
479
+ "host key does not match the one in known_hosts; this "
480
+ "may be a possible attack");
481
goto out;
482
- case LIBSSH2_KNOWNHOST_CHECK_NOTFOUND:
483
+ case SSH_SERVER_FOUND_OTHER:
484
ret = -EINVAL;
485
- session_error_setg(errp, s, "no host key was found in known_hosts");
486
+ error_setg(errp,
487
+ "host key for this server not found, another type exists");
488
+ goto out;
489
+ case SSH_SERVER_FILE_NOT_FOUND:
490
+ ret = -ENOENT;
491
+ error_setg(errp, "known_hosts file not found");
492
goto out;
493
- case LIBSSH2_KNOWNHOST_CHECK_FAILURE:
494
+ case SSH_SERVER_NOT_KNOWN:
495
ret = -EINVAL;
496
- session_error_setg(errp, s,
497
- "failure matching the host key with known_hosts");
498
+ error_setg(errp, "no host key was found in known_hosts");
499
+ goto out;
500
+ case SSH_SERVER_ERROR:
501
+ ret = -EINVAL;
502
+ error_setg(errp, "server error");
503
goto out;
504
default:
505
ret = -EINVAL;
506
- session_error_setg(errp, s, "unknown error matching the host key"
507
- " with known_hosts (%d)", r);
508
+ error_setg(errp, "error while checking for known server (%d)", state);
509
goto out;
510
}
511
+#endif /* !HAVE_LIBSSH_0_8 */
512
513
/* known_hosts checking successful. */
514
ret = 0;
515
516
out:
517
- if (knh != NULL) {
518
- libssh2_knownhost_free(knh);
519
- }
520
- g_free(knh_file);
521
return ret;
522
}
523
524
@@ -XXX,XX +XXX,XX @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,
525
526
static int
527
check_host_key_hash(BDRVSSHState *s, const char *hash,
528
- int hash_type, size_t fingerprint_len, Error **errp)
529
+ enum ssh_publickey_hash_type type, Error **errp)
530
{
531
- const char *fingerprint;
532
-
533
- fingerprint = libssh2_hostkey_hash(s->session, hash_type);
534
- if (!fingerprint) {
535
+ int r;
536
+ ssh_key pubkey;
537
+ unsigned char *server_hash;
538
+ size_t server_hash_len;
539
+
540
+#ifdef HAVE_LIBSSH_0_8
541
+ r = ssh_get_server_publickey(s->session, &pubkey);
542
+#else
543
+ r = ssh_get_publickey(s->session, &pubkey);
544
+#endif
545
+ if (r != SSH_OK) {
546
session_error_setg(errp, s, "failed to read remote host key");
547
return -EINVAL;
548
}
549
550
- if(compare_fingerprint((unsigned char *) fingerprint, fingerprint_len,
551
- hash) != 0) {
552
+ r = ssh_get_publickey_hash(pubkey, type, &server_hash, &server_hash_len);
553
+ ssh_key_free(pubkey);
554
+ if (r != 0) {
555
+ session_error_setg(errp, s,
556
+ "failed reading the hash of the server SSH key");
557
+ return -EINVAL;
558
+ }
559
+
560
+ r = compare_fingerprint(server_hash, server_hash_len, hash);
561
+ ssh_clean_pubkey_hash(&server_hash);
562
+ if (r != 0) {
563
error_setg(errp, "remote host key does not match host_key_check '%s'",
564
hash);
565
return -EPERM;
566
@@ -XXX,XX +XXX,XX @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
567
return 0;
568
}
569
570
-static int check_host_key(BDRVSSHState *s, const char *host, int port,
571
- SshHostKeyCheck *hkc, Error **errp)
572
+static int check_host_key(BDRVSSHState *s, SshHostKeyCheck *hkc, Error **errp)
573
{
574
SshHostKeyCheckMode mode;
575
576
@@ -XXX,XX +XXX,XX @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
577
case SSH_HOST_KEY_CHECK_MODE_HASH:
578
if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_MD5) {
579
return check_host_key_hash(s, hkc->u.hash.hash,
580
- LIBSSH2_HOSTKEY_HASH_MD5, 16, errp);
581
+ SSH_PUBLICKEY_HASH_MD5, errp);
582
} else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA1) {
583
return check_host_key_hash(s, hkc->u.hash.hash,
584
- LIBSSH2_HOSTKEY_HASH_SHA1, 20, errp);
585
+ SSH_PUBLICKEY_HASH_SHA1, errp);
100
}
586
}
101
587
g_assert_not_reached();
588
break;
589
case SSH_HOST_KEY_CHECK_MODE_KNOWN_HOSTS:
590
- return check_host_key_knownhosts(s, host, port, errp);
591
+ return check_host_key_knownhosts(s, errp);
592
default:
593
g_assert_not_reached();
594
}
595
@@ -XXX,XX +XXX,XX @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
596
return -EINVAL;
597
}
598
599
-static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
600
+static int authenticate(BDRVSSHState *s, Error **errp)
601
{
602
int r, ret;
603
- const char *userauthlist;
604
- LIBSSH2_AGENT *agent = NULL;
605
- struct libssh2_agent_publickey *identity;
606
- struct libssh2_agent_publickey *prev_identity = NULL;
607
+ int method;
608
609
- userauthlist = libssh2_userauth_list(s->session, user, strlen(user));
610
- if (strstr(userauthlist, "publickey") == NULL) {
611
+ /* Try to authenticate with the "none" method. */
612
+ r = ssh_userauth_none(s->session, NULL);
613
+ if (r == SSH_AUTH_ERROR) {
614
ret = -EPERM;
615
- error_setg(errp,
616
- "remote server does not support \"publickey\" authentication");
617
+ session_error_setg(errp, s, "failed to authenticate using none "
618
+ "authentication");
619
goto out;
620
- }
621
-
622
- /* Connect to ssh-agent and try each identity in turn. */
623
- agent = libssh2_agent_init(s->session);
624
- if (!agent) {
625
- ret = -EINVAL;
626
- session_error_setg(errp, s, "failed to initialize ssh-agent support");
627
- goto out;
628
- }
629
- if (libssh2_agent_connect(agent)) {
630
- ret = -ECONNREFUSED;
631
- session_error_setg(errp, s, "failed to connect to ssh-agent");
632
- goto out;
633
- }
634
- if (libssh2_agent_list_identities(agent)) {
635
- ret = -EINVAL;
636
- session_error_setg(errp, s,
637
- "failed requesting identities from ssh-agent");
638
+ } else if (r == SSH_AUTH_SUCCESS) {
639
+ /* Authenticated! */
640
+ ret = 0;
641
goto out;
642
}
643
644
- for(;;) {
645
- r = libssh2_agent_get_identity(agent, &identity, prev_identity);
646
- if (r == 1) { /* end of list */
647
- break;
648
- }
649
- if (r < 0) {
650
+ method = ssh_userauth_list(s->session, NULL);
651
+ trace_ssh_auth_methods(method);
652
+
653
+ /*
654
+ * Try to authenticate with publickey, using the ssh-agent
655
+ * if available.
656
+ */
657
+ if (method & SSH_AUTH_METHOD_PUBLICKEY) {
658
+ r = ssh_userauth_publickey_auto(s->session, NULL, NULL);
659
+ if (r == SSH_AUTH_ERROR) {
660
ret = -EINVAL;
661
- session_error_setg(errp, s,
662
- "failed to obtain identity from ssh-agent");
663
+ session_error_setg(errp, s, "failed to authenticate using "
664
+ "publickey authentication");
665
goto out;
666
- }
667
- r = libssh2_agent_userauth(agent, user, identity);
668
- if (r == 0) {
669
+ } else if (r == SSH_AUTH_SUCCESS) {
670
/* Authenticated! */
671
ret = 0;
672
goto out;
673
}
674
- /* Failed to authenticate with this identity, try the next one. */
675
- prev_identity = identity;
676
}
677
678
ret = -EPERM;
679
@@ -XXX,XX +XXX,XX @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
680
"and the identities held by your ssh-agent");
681
682
out:
683
- if (agent != NULL) {
684
- /* Note: libssh2 implementation implicitly calls
685
- * libssh2_agent_disconnect if necessary.
686
- */
687
- libssh2_agent_free(agent);
688
- }
689
-
690
return ret;
691
}
692
693
@@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
694
int ssh_flags, int creat_mode, Error **errp)
695
{
696
int r, ret;
697
- long port = 0;
698
+ unsigned int port = 0;
699
+ int new_sock = -1;
700
701
if (opts->has_user) {
702
s->user = g_strdup(opts->user);
703
@@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
704
s->inet = opts->server;
705
opts->server = NULL;
706
707
- if (qemu_strtol(s->inet->port, NULL, 10, &port) < 0) {
708
+ if (qemu_strtoui(s->inet->port, NULL, 10, &port) < 0) {
709
error_setg(errp, "Use only numeric port value");
710
ret = -EINVAL;
711
goto err;
712
}
713
714
/* Open the socket and connect. */
715
- s->sock = inet_connect_saddr(s->inet, errp);
716
- if (s->sock < 0) {
717
+ new_sock = inet_connect_saddr(s->inet, errp);
718
+ if (new_sock < 0) {
719
ret = -EIO;
720
goto err;
721
}
722
723
+ /*
724
+ * Try to disable the Nagle algorithm on TCP sockets to reduce latency,
725
+ * but do not fail if it cannot be disabled.
726
+ */
727
+ r = socket_set_nodelay(new_sock);
728
+ if (r < 0) {
729
+ warn_report("can't set TCP_NODELAY for the ssh server %s: %s",
730
+ s->inet->host, strerror(errno));
731
+ }
732
+
733
/* Create SSH session. */
734
- s->session = libssh2_session_init();
735
+ s->session = ssh_new();
736
if (!s->session) {
737
ret = -EINVAL;
738
- session_error_setg(errp, s, "failed to initialize libssh2 session");
739
+ session_error_setg(errp, s, "failed to initialize libssh session");
740
goto err;
741
}
742
743
-#if TRACE_LIBSSH2 != 0
744
- libssh2_trace(s->session, TRACE_LIBSSH2);
745
-#endif
746
+ /*
747
+ * Make sure we are in blocking mode during the connection and
748
+ * authentication phases.
749
+ */
750
+ ssh_set_blocking(s->session, 1);
751
752
- r = libssh2_session_handshake(s->session, s->sock);
753
- if (r != 0) {
754
+ r = ssh_options_set(s->session, SSH_OPTIONS_USER, s->user);
755
+ if (r < 0) {
756
+ ret = -EINVAL;
757
+ session_error_setg(errp, s,
758
+ "failed to set the user in the libssh session");
759
+ goto err;
760
+ }
761
+
762
+ r = ssh_options_set(s->session, SSH_OPTIONS_HOST, s->inet->host);
763
+ if (r < 0) {
764
+ ret = -EINVAL;
765
+ session_error_setg(errp, s,
766
+ "failed to set the host in the libssh session");
767
+ goto err;
768
+ }
769
+
770
+ if (port > 0) {
771
+ r = ssh_options_set(s->session, SSH_OPTIONS_PORT, &port);
772
+ if (r < 0) {
773
+ ret = -EINVAL;
774
+ session_error_setg(errp, s,
775
+ "failed to set the port in the libssh session");
776
+ goto err;
777
+ }
778
+ }
779
+
780
+ r = ssh_options_set(s->session, SSH_OPTIONS_COMPRESSION, "none");
781
+ if (r < 0) {
782
+ ret = -EINVAL;
783
+ session_error_setg(errp, s,
784
+ "failed to disable the compression in the libssh "
785
+ "session");
786
+ goto err;
787
+ }
788
+
789
+ /* Read ~/.ssh/config. */
790
+ r = ssh_options_parse_config(s->session, NULL);
791
+ if (r < 0) {
792
+ ret = -EINVAL;
793
+ session_error_setg(errp, s, "failed to parse ~/.ssh/config");
794
+ goto err;
795
+ }
796
+
797
+ r = ssh_options_set(s->session, SSH_OPTIONS_FD, &new_sock);
798
+ if (r < 0) {
799
+ ret = -EINVAL;
800
+ session_error_setg(errp, s,
801
+ "failed to set the socket in the libssh session");
802
+ goto err;
803
+ }
804
+ /* libssh took ownership of the socket. */
805
+ s->sock = new_sock;
806
+ new_sock = -1;
807
+
808
+ /* Connect. */
809
+ r = ssh_connect(s->session);
810
+ if (r != SSH_OK) {
811
ret = -EINVAL;
812
session_error_setg(errp, s, "failed to establish SSH session");
813
goto err;
814
}
815
816
/* Check the remote host's key against known_hosts. */
817
- ret = check_host_key(s, s->inet->host, port, opts->host_key_check, errp);
818
+ ret = check_host_key(s, opts->host_key_check, errp);
819
if (ret < 0) {
820
goto err;
821
}
822
823
/* Authenticate. */
824
- ret = authenticate(s, s->user, errp);
825
+ ret = authenticate(s, errp);
826
if (ret < 0) {
827
goto err;
828
}
829
830
/* Start SFTP. */
831
- s->sftp = libssh2_sftp_init(s->session);
832
+ s->sftp = sftp_new(s->session);
833
if (!s->sftp) {
834
- session_error_setg(errp, s, "failed to initialize sftp handle");
835
+ session_error_setg(errp, s, "failed to create sftp handle");
836
+ ret = -EINVAL;
837
+ goto err;
838
+ }
839
+
840
+ r = sftp_init(s->sftp);
841
+ if (r < 0) {
842
+ sftp_error_setg(errp, s, "failed to initialize sftp handle");
843
ret = -EINVAL;
844
goto err;
845
}
846
847
/* Open the remote file. */
848
trace_ssh_connect_to_ssh(opts->path, ssh_flags, creat_mode);
849
- s->sftp_handle = libssh2_sftp_open(s->sftp, opts->path, ssh_flags,
850
- creat_mode);
851
+ s->sftp_handle = sftp_open(s->sftp, opts->path, ssh_flags, creat_mode);
852
if (!s->sftp_handle) {
853
- session_error_setg(errp, s, "failed to open remote file '%s'",
854
- opts->path);
855
+ sftp_error_setg(errp, s, "failed to open remote file '%s'",
856
+ opts->path);
857
ret = -EINVAL;
858
goto err;
859
}
860
861
- r = libssh2_sftp_fstat(s->sftp_handle, &s->attrs);
862
- if (r < 0) {
863
+ /* Make sure the SFTP file is handled in blocking mode. */
864
+ sftp_file_set_blocking(s->sftp_handle);
865
+
866
+ s->attrs = sftp_fstat(s->sftp_handle);
867
+ if (!s->attrs) {
868
sftp_error_setg(errp, s, "failed to read file attributes");
869
return -EINVAL;
870
}
871
@@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
872
return 0;
873
874
err:
875
+ if (s->attrs) {
876
+ sftp_attributes_free(s->attrs);
877
+ }
878
+ s->attrs = NULL;
879
if (s->sftp_handle) {
880
- libssh2_sftp_close(s->sftp_handle);
881
+ sftp_close(s->sftp_handle);
882
}
883
s->sftp_handle = NULL;
884
if (s->sftp) {
885
- libssh2_sftp_shutdown(s->sftp);
886
+ sftp_free(s->sftp);
887
}
888
s->sftp = NULL;
889
if (s->session) {
890
- libssh2_session_disconnect(s->session,
891
- "from qemu ssh client: "
892
- "error opening connection");
893
- libssh2_session_free(s->session);
894
+ ssh_disconnect(s->session);
895
+ ssh_free(s->session);
896
}
897
s->session = NULL;
898
+ s->sock = -1;
899
+ if (new_sock >= 0) {
900
+ close(new_sock);
901
+ }
902
903
return ret;
904
}
905
@@ -XXX,XX +XXX,XX @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
906
907
ssh_state_init(s);
908
909
- ssh_flags = LIBSSH2_FXF_READ;
910
+ ssh_flags = 0;
911
if (bdrv_flags & BDRV_O_RDWR) {
912
- ssh_flags |= LIBSSH2_FXF_WRITE;
913
+ ssh_flags |= O_RDWR;
914
+ } else {
915
+ ssh_flags |= O_RDONLY;
916
}
917
918
opts = ssh_parse_options(options, errp);
919
@@ -XXX,XX +XXX,XX @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
920
}
921
922
/* Go non-blocking. */
923
- libssh2_session_set_blocking(s->session, 0);
924
+ ssh_set_blocking(s->session, 0);
925
926
qapi_free_BlockdevOptionsSsh(opts);
927
928
return 0;
929
930
err:
931
- if (s->sock >= 0) {
932
- close(s->sock);
933
- }
934
- s->sock = -1;
935
-
936
qapi_free_BlockdevOptionsSsh(opts);
937
938
return ret;
939
@@ -XXX,XX +XXX,XX @@ static int ssh_grow_file(BDRVSSHState *s, int64_t offset, Error **errp)
940
{
941
ssize_t ret;
942
char c[1] = { '\0' };
943
- int was_blocking = libssh2_session_get_blocking(s->session);
944
+ int was_blocking = ssh_is_blocking(s->session);
945
946
/* offset must be strictly greater than the current size so we do
947
* not overwrite anything */
948
- assert(offset > 0 && offset > s->attrs.filesize);
949
+ assert(offset > 0 && offset > s->attrs->size);
950
951
- libssh2_session_set_blocking(s->session, 1);
952
+ ssh_set_blocking(s->session, 1);
953
954
- libssh2_sftp_seek64(s->sftp_handle, offset - 1);
955
- ret = libssh2_sftp_write(s->sftp_handle, c, 1);
956
+ sftp_seek64(s->sftp_handle, offset - 1);
957
+ ret = sftp_write(s->sftp_handle, c, 1);
958
959
- libssh2_session_set_blocking(s->session, was_blocking);
960
+ ssh_set_blocking(s->session, was_blocking);
961
962
if (ret < 0) {
963
sftp_error_setg(errp, s, "Failed to grow file");
964
return -EIO;
965
}
966
967
- s->attrs.filesize = offset;
968
+ s->attrs->size = offset;
969
return 0;
970
}
971
972
@@ -XXX,XX +XXX,XX @@ static int ssh_co_create(BlockdevCreateOptions *options, Error **errp)
973
ssh_state_init(&s);
974
975
ret = connect_to_ssh(&s, opts->location,
976
- LIBSSH2_FXF_READ|LIBSSH2_FXF_WRITE|
977
- LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC,
978
+ O_RDWR | O_CREAT | O_TRUNC,
979
0644, errp);
980
if (ret < 0) {
981
goto fail;
982
@@ -XXX,XX +XXX,XX @@ static int ssh_has_zero_init(BlockDriverState *bs)
983
/* Assume false, unless we can positively prove it's true. */
984
int has_zero_init = 0;
985
986
- if (s->attrs.flags & LIBSSH2_SFTP_ATTR_PERMISSIONS) {
987
- if (s->attrs.permissions & LIBSSH2_SFTP_S_IFREG) {
988
- has_zero_init = 1;
989
- }
990
+ if (s->attrs->type == SSH_FILEXFER_TYPE_REGULAR) {
991
+ has_zero_init = 1;
992
}
993
994
return has_zero_init;
995
@@ -XXX,XX +XXX,XX @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
996
.co = qemu_coroutine_self()
997
};
998
999
- r = libssh2_session_block_directions(s->session);
1000
+ r = ssh_get_poll_flags(s->session);
1001
1002
- if (r & LIBSSH2_SESSION_BLOCK_INBOUND) {
1003
+ if (r & SSH_READ_PENDING) {
1004
rd_handler = restart_coroutine;
1005
}
1006
- if (r & LIBSSH2_SESSION_BLOCK_OUTBOUND) {
1007
+ if (r & SSH_WRITE_PENDING) {
1008
wr_handler = restart_coroutine;
1009
}
1010
1011
@@ -XXX,XX +XXX,XX @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
1012
trace_ssh_co_yield_back(s->sock);
1013
}
1014
1015
-/* SFTP has a function `libssh2_sftp_seek64' which seeks to a position
1016
- * in the remote file. Notice that it just updates a field in the
1017
- * sftp_handle structure, so there is no network traffic and it cannot
1018
- * fail.
1019
- *
1020
- * However, `libssh2_sftp_seek64' does have a catastrophic effect on
1021
- * performance since it causes the handle to throw away all in-flight
1022
- * reads and buffered readahead data. Therefore this function tries
1023
- * to be intelligent about when to call the underlying libssh2 function.
1024
- */
1025
-#define SSH_SEEK_WRITE 0
1026
-#define SSH_SEEK_READ 1
1027
-#define SSH_SEEK_FORCE 2
1028
-
1029
-static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags)
1030
-{
1031
- bool op_read = (flags & SSH_SEEK_READ) != 0;
1032
- bool force = (flags & SSH_SEEK_FORCE) != 0;
1033
-
1034
- if (force || op_read != s->offset_op_read || offset != s->offset) {
1035
- trace_ssh_seek(offset);
1036
- libssh2_sftp_seek64(s->sftp_handle, offset);
1037
- s->offset = offset;
1038
- s->offset_op_read = op_read;
1039
- }
1040
-}
1041
-
1042
static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
1043
int64_t offset, size_t size,
1044
QEMUIOVector *qiov)
1045
@@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
1046
1047
trace_ssh_read(offset, size);
1048
1049
- ssh_seek(s, offset, SSH_SEEK_READ);
1050
+ trace_ssh_seek(offset);
1051
+ sftp_seek64(s->sftp_handle, offset);
1052
1053
/* This keeps track of the current iovec element ('i'), where we
1054
* will write to next ('buf'), and the end of the current iovec
1055
@@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
1056
buf = i->iov_base;
1057
end_of_vec = i->iov_base + i->iov_len;
1058
1059
- /* libssh2 has a hard-coded limit of 2000 bytes per request,
1060
- * although it will also do readahead behind our backs. Therefore
1061
- * we may have to do repeated reads here until we have read 'size'
1062
- * bytes.
1063
- */
1064
for (got = 0; got < size; ) {
1065
+ size_t request_read_size;
1066
again:
1067
- trace_ssh_read_buf(buf, end_of_vec - buf);
1068
- r = libssh2_sftp_read(s->sftp_handle, buf, end_of_vec - buf);
1069
- trace_ssh_read_return(r);
102
+ /*
1070
+ /*
103
+ * This cluster is allocated, so we need to create a refblock
1071
+ * The size of SFTP packets is limited to 32K bytes, so limit
104
+ * for it. The data we will write to disk is just the
1072
+ * the amount of data requested to 16K, as libssh currently
105
+ * respective slice from *refcount_table, so it will contain
1073
+ * does not handle multiple requests on its own.
106
+ * accurate refcounts for all clusters belonging to this
107
+ * refblock. After we have written it, we will therefore skip
108
+ * all remaining clusters in this refblock.
109
+ */
1074
+ */
110
+
1075
+ request_read_size = MIN(end_of_vec - buf, 16384);
111
refblock_index = cluster >> s->refcount_block_bits;
1076
+ trace_ssh_read_buf(buf, end_of_vec - buf, request_read_size);
112
refblock_start = refblock_index << s->refcount_block_bits;
1077
+ r = sftp_read(s->sftp_handle, buf, request_read_size);
113
1078
+ trace_ssh_read_return(r, sftp_get_error(s->sftp));
114
- /* Don't allocate a cluster in a refblock already written to disk */
1079
115
- if (first_free_cluster < refblock_start) {
1080
- if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
116
- first_free_cluster = refblock_start;
1081
+ if (r == SSH_AGAIN) {
1082
co_yield(s, bs);
1083
goto again;
1084
}
1085
- if (r < 0) {
1086
- sftp_error_trace(s, "read");
1087
- s->offset = -1;
1088
- return -EIO;
117
- }
1089
- }
118
- refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table,
1090
- if (r == 0) {
119
- nb_clusters, &first_free_cluster);
1091
+ if (r == SSH_EOF || (r == 0 && sftp_get_error(s->sftp) == SSH_FX_EOF)) {
120
- if (refblock_offset < 0) {
1092
/* EOF: Short read so pad the buffer with zeroes and return it. */
121
- fprintf(stderr, "ERROR allocating refblock: %s\n",
1093
qemu_iovec_memset(qiov, got, 0, size - got);
122
- strerror(-refblock_offset));
1094
return 0;
123
- res->check_errors++;
1095
}
124
- ret = refblock_offset;
1096
+ if (r <= 0) {
125
- goto fail;
1097
+ sftp_error_trace(s, "read");
1098
+ return -EIO;
1099
+ }
1100
1101
got += r;
1102
buf += r;
1103
- s->offset += r;
1104
if (buf >= end_of_vec && got < size) {
1105
i++;
1106
buf = i->iov_base;
1107
@@ -XXX,XX +XXX,XX @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
1108
1109
trace_ssh_write(offset, size);
1110
1111
- ssh_seek(s, offset, SSH_SEEK_WRITE);
1112
+ trace_ssh_seek(offset);
1113
+ sftp_seek64(s->sftp_handle, offset);
1114
1115
/* This keeps track of the current iovec element ('i'), where we
1116
* will read from next ('buf'), and the end of the current iovec
1117
@@ -XXX,XX +XXX,XX @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
1118
end_of_vec = i->iov_base + i->iov_len;
1119
1120
for (written = 0; written < size; ) {
1121
+ size_t request_write_size;
1122
again:
1123
- trace_ssh_write_buf(buf, end_of_vec - buf);
1124
- r = libssh2_sftp_write(s->sftp_handle, buf, end_of_vec - buf);
1125
- trace_ssh_write_return(r);
1126
+ /*
1127
+ * Avoid too large data packets, as libssh currently does not
1128
+ * handle multiple requests on its own.
1129
+ */
1130
+ request_write_size = MIN(end_of_vec - buf, 131072);
1131
+ trace_ssh_write_buf(buf, end_of_vec - buf, request_write_size);
1132
+ r = sftp_write(s->sftp_handle, buf, request_write_size);
1133
+ trace_ssh_write_return(r, sftp_get_error(s->sftp));
1134
1135
- if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
1136
+ if (r == SSH_AGAIN) {
1137
co_yield(s, bs);
1138
goto again;
1139
}
1140
if (r < 0) {
1141
sftp_error_trace(s, "write");
1142
- s->offset = -1;
1143
return -EIO;
1144
}
1145
- /* The libssh2 API is very unclear about this. A comment in
1146
- * the code says "nothing was acked, and no EAGAIN was
1147
- * received!" which apparently means that no data got sent
1148
- * out, and the underlying channel didn't return any EAGAIN
1149
- * indication. I think this is a bug in either libssh2 or
1150
- * OpenSSH (server-side). In any case, forcing a seek (to
1151
- * discard libssh2 internal buffers), and then trying again
1152
- * works for me.
1153
- */
1154
- if (r == 0) {
1155
- ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE);
1156
- co_yield(s, bs);
1157
- goto again;
126
- }
1158
- }
127
+ if (on_disk_reftable_entries > refblock_index &&
1159
128
+ on_disk_reftable[refblock_index])
1160
written += r;
129
+ {
1161
buf += r;
130
+ /*
1162
- s->offset += r;
131
+ * We can get here after a `goto write_refblocks`: We have a
1163
if (buf >= end_of_vec && written < size) {
132
+ * reftable from a previous run, and the refblock is already
1164
i++;
133
+ * allocated. No need to allocate it again.
1165
buf = i->iov_base;
134
+ */
1166
end_of_vec = i->iov_base + i->iov_len;
135
+ refblock_offset = on_disk_reftable[refblock_index];
136
+ } else {
137
+ int64_t refblock_cluster_index;
138
139
- if (reftable_size <= refblock_index) {
140
- uint32_t old_reftable_size = reftable_size;
141
- uint64_t *new_on_disk_reftable;
142
+ /* Don't allocate a cluster in a refblock already written to disk */
143
+ if (first_free_cluster < refblock_start) {
144
+ first_free_cluster = refblock_start;
145
+ }
146
+ refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table,
147
+ nb_clusters,
148
+ &first_free_cluster);
149
+ if (refblock_offset < 0) {
150
+ fprintf(stderr, "ERROR allocating refblock: %s\n",
151
+ strerror(-refblock_offset));
152
+ return refblock_offset;
153
+ }
154
155
- reftable_size = ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE,
156
- s->cluster_size) / REFTABLE_ENTRY_SIZE;
157
- new_on_disk_reftable = g_try_realloc(on_disk_reftable,
158
- reftable_size *
159
- REFTABLE_ENTRY_SIZE);
160
- if (!new_on_disk_reftable) {
161
- res->check_errors++;
162
- ret = -ENOMEM;
163
- goto fail;
164
+ refblock_cluster_index = refblock_offset / s->cluster_size;
165
+ if (refblock_cluster_index >= end_cluster) {
166
+ /*
167
+ * We must write the refblock that holds this refblock's
168
+ * refcount
169
+ */
170
+ end_cluster = refblock_cluster_index + 1;
171
}
172
- on_disk_reftable = new_on_disk_reftable;
173
174
- memset(on_disk_reftable + old_reftable_size, 0,
175
- (reftable_size - old_reftable_size) * REFTABLE_ENTRY_SIZE);
176
+ if (on_disk_reftable_entries <= refblock_index) {
177
+ on_disk_reftable_entries =
178
+ ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE,
179
+ s->cluster_size) / REFTABLE_ENTRY_SIZE;
180
+ on_disk_reftable =
181
+ g_try_realloc(on_disk_reftable,
182
+ on_disk_reftable_entries *
183
+ REFTABLE_ENTRY_SIZE);
184
+ if (!on_disk_reftable) {
185
+ return -ENOMEM;
186
+ }
187
188
- /* The offset we have for the reftable is now no longer valid;
189
- * this will leak that range, but we can easily fix that by running
190
- * a leak-fixing check after this rebuild operation */
191
- reftable_offset = -1;
192
- } else {
193
- assert(on_disk_reftable);
194
- }
195
- on_disk_reftable[refblock_index] = refblock_offset;
196
+ memset(on_disk_reftable + *on_disk_reftable_entries_ptr, 0,
197
+ (on_disk_reftable_entries -
198
+ *on_disk_reftable_entries_ptr) *
199
+ REFTABLE_ENTRY_SIZE);
200
201
- /* If this is apparently the last refblock (for now), try to squeeze the
202
- * reftable in */
203
- if (refblock_index == (*nb_clusters - 1) >> s->refcount_block_bits &&
204
- reftable_offset < 0)
205
- {
206
- uint64_t reftable_clusters = size_to_clusters(s, reftable_size *
207
- REFTABLE_ENTRY_SIZE);
208
- reftable_offset = alloc_clusters_imrt(bs, reftable_clusters,
209
- refcount_table, nb_clusters,
210
- &first_free_cluster);
211
- if (reftable_offset < 0) {
212
- fprintf(stderr, "ERROR allocating reftable: %s\n",
213
- strerror(-reftable_offset));
214
- res->check_errors++;
215
- ret = reftable_offset;
216
- goto fail;
217
+ *on_disk_reftable_ptr = on_disk_reftable;
218
+ *on_disk_reftable_entries_ptr = on_disk_reftable_entries;
219
+
220
+ reftable_grown = true;
221
+ } else {
222
+ assert(on_disk_reftable);
223
}
224
+ on_disk_reftable[refblock_index] = refblock_offset;
225
}
1167
}
226
1168
227
+ /* Refblock is allocated, write it to disk */
1169
- if (offset + written > s->attrs.filesize)
228
+
1170
- s->attrs.filesize = offset + written;
229
ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset,
1171
+ if (offset + written > s->attrs->size) {
230
s->cluster_size, false);
1172
+ s->attrs->size = offset + written;
231
if (ret < 0) {
1173
+ }
232
fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
1174
}
233
- goto fail;
1175
234
+ return ret;
1176
return 0;
235
}
1177
@@ -XXX,XX +XXX,XX @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)
236
1178
}
237
- /* The size of *refcount_table is always cluster-aligned, therefore the
1179
}
238
- * write operation will not overflow */
1180
239
+ /*
1181
-#ifdef HAS_LIBSSH2_SFTP_FSYNC
240
+ * The refblock is simply a slice of *refcount_table.
1182
+#ifdef HAVE_LIBSSH_0_8
241
+ * Note that the size of *refcount_table is always aligned to
1183
242
+ * whole clusters, so the write operation will not result in
1184
static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
243
+ * out-of-bounds accesses.
1185
{
244
+ */
1186
int r;
245
on_disk_refblock = (void *)((char *) *refcount_table +
1187
246
refblock_index * s->cluster_size);
1188
trace_ssh_flush();
247
1189
+
248
@@ -XXX,XX +XXX,XX @@ write_refblocks:
1190
+ if (!sftp_extension_supported(s->sftp, "fsync@openssh.com", "1")) {
249
s->cluster_size);
1191
+ unsafe_flush_warning(s, "OpenSSH >= 6.3");
250
if (ret < 0) {
1192
+ return 0;
251
fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
252
- goto fail;
253
+ return ret;
254
}
255
256
- /* Go to the end of this refblock */
257
+ /* This refblock is done, skip to its end */
258
cluster = refblock_start + s->refcount_block_size - 1;
259
}
260
261
- if (reftable_offset < 0) {
262
- uint64_t post_refblock_start, reftable_clusters;
263
+ return reftable_grown;
264
+}
265
+
266
+/*
267
+ * Creates a new refcount structure based solely on the in-memory information
268
+ * given through *refcount_table (this in-memory information is basically just
269
+ * the concatenation of all refblocks). All necessary allocations will be
270
+ * reflected in that array.
271
+ *
272
+ * On success, the old refcount structure is leaked (it will be covered by the
273
+ * new refcount structure).
274
+ */
275
+static int rebuild_refcount_structure(BlockDriverState *bs,
276
+ BdrvCheckResult *res,
277
+ void **refcount_table,
278
+ int64_t *nb_clusters)
279
+{
280
+ BDRVQcow2State *s = bs->opaque;
281
+ int64_t reftable_offset = -1;
282
+ int64_t reftable_length = 0;
283
+ int64_t reftable_clusters;
284
+ int64_t refblock_index;
285
+ uint32_t on_disk_reftable_entries = 0;
286
+ uint64_t *on_disk_reftable = NULL;
287
+ int ret = 0;
288
+ int reftable_size_changed = 0;
289
+ struct {
290
+ uint64_t reftable_offset;
291
+ uint32_t reftable_clusters;
292
+ } QEMU_PACKED reftable_offset_and_clusters;
293
+
294
+ qcow2_cache_empty(bs, s->refcount_block_cache);
295
+
296
+ /*
297
+ * For each refblock containing entries, we try to allocate a
298
+ * cluster (in the in-memory refcount table) and write its offset
299
+ * into on_disk_reftable[]. We then write the whole refblock to
300
+ * disk (as a slice of the in-memory refcount table).
301
+ * This is done by rebuild_refcounts_write_refblocks().
302
+ *
303
+ * Once we have scanned all clusters, we try to find space for the
304
+ * reftable. This will dirty the in-memory refcount table (i.e.
305
+ * make it differ from the refblocks we have already written), so we
306
+ * need to run rebuild_refcounts_write_refblocks() again for the
307
+ * range of clusters where the reftable has been allocated.
308
+ *
309
+ * This second run might make the reftable grow again, in which case
310
+ * we will need to allocate another space for it, which is why we
311
+ * repeat all this until the reftable stops growing.
312
+ *
313
+ * (This loop will terminate, because with every cluster the
314
+ * reftable grows, it can accomodate a multitude of more refcounts,
315
+ * so that at some point this must be able to cover the reftable
316
+ * and all refblocks describing it.)
317
+ *
318
+ * We then convert the reftable to big-endian and write it to disk.
319
+ *
320
+ * Note that we never free any reftable allocations. Doing so would
321
+ * needlessly complicate the algorithm: The eventual second check
322
+ * run we do will clean up all leaks we have caused.
323
+ */
324
+
325
+ reftable_size_changed =
326
+ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,
327
+ 0, *nb_clusters,
328
+ &on_disk_reftable,
329
+ &on_disk_reftable_entries);
330
+ if (reftable_size_changed < 0) {
331
+ res->check_errors++;
332
+ ret = reftable_size_changed;
333
+ goto fail;
334
+ }
1193
+ }
335
+
1194
again:
336
+ /*
1195
- r = libssh2_sftp_fsync(s->sftp_handle);
337
+ * There was no reftable before, so rebuild_refcounts_write_refblocks()
1196
- if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
338
+ * must have increased its size (from 0 to something).
1197
+ r = sftp_fsync(s->sftp_handle);
339
+ */
1198
+ if (r == SSH_AGAIN) {
340
+ assert(reftable_size_changed);
1199
co_yield(s, bs);
341
+
1200
goto again;
342
+ do {
1201
}
343
+ int64_t reftable_start_cluster, reftable_end_cluster;
1202
- if (r == LIBSSH2_ERROR_SFTP_PROTOCOL &&
344
+ int64_t first_free_cluster = 0;
1203
- libssh2_sftp_last_error(s->sftp) == LIBSSH2_FX_OP_UNSUPPORTED) {
345
+
1204
- unsafe_flush_warning(s, "OpenSSH >= 6.3");
346
+ reftable_length = on_disk_reftable_entries * REFTABLE_ENTRY_SIZE;
1205
- return 0;
347
+ reftable_clusters = size_to_clusters(s, reftable_length);
348
349
- post_refblock_start = ROUND_UP(*nb_clusters, s->refcount_block_size);
350
- reftable_clusters =
351
- size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE);
352
- /* Not pretty but simple */
353
- if (first_free_cluster < post_refblock_start) {
354
- first_free_cluster = post_refblock_start;
355
- }
356
reftable_offset = alloc_clusters_imrt(bs, reftable_clusters,
357
refcount_table, nb_clusters,
358
&first_free_cluster);
359
@@ -XXX,XX +XXX,XX @@ write_refblocks:
360
goto fail;
361
}
362
363
- goto write_refblocks;
364
- }
1206
- }
365
+ /*
1207
if (r < 0) {
366
+ * We need to update the affected refblocks, so re-run the
1208
sftp_error_trace(s, "fsync");
367
+ * write_refblocks loop for the reftable's range of clusters.
1209
return -EIO;
368
+ */
1210
@@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
369
+ assert(offset_into_cluster(s, reftable_offset) == 0);
1211
return ret;
370
+ reftable_start_cluster = reftable_offset / s->cluster_size;
1212
}
371
+ reftable_end_cluster = reftable_start_cluster + reftable_clusters;
1213
372
+ reftable_size_changed =
1214
-#else /* !HAS_LIBSSH2_SFTP_FSYNC */
373
+ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,
1215
+#else /* !HAVE_LIBSSH_0_8 */
374
+ reftable_start_cluster,
1216
375
+ reftable_end_cluster,
1217
static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
376
+ &on_disk_reftable,
1218
{
377
+ &on_disk_reftable_entries);
1219
BDRVSSHState *s = bs->opaque;
378
+ if (reftable_size_changed < 0) {
1220
379
+ res->check_errors++;
1221
- unsafe_flush_warning(s, "libssh2 >= 1.4.4");
380
+ ret = reftable_size_changed;
1222
+ unsafe_flush_warning(s, "libssh >= 0.8.0");
381
+ goto fail;
382
+ }
383
+
384
+ /*
385
+ * If the reftable size has changed, we will need to find a new
386
+ * allocation, repeating the loop.
387
+ */
388
+ } while (reftable_size_changed);
389
390
- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {
391
+ /* The above loop must have run at least once */
392
+ assert(reftable_offset >= 0);
393
+
394
+ /*
395
+ * All allocations are done, all refblocks are written, convert the
396
+ * reftable to big-endian and write it to disk.
397
+ */
398
+
399
+ for (refblock_index = 0; refblock_index < on_disk_reftable_entries;
400
+ refblock_index++)
401
+ {
402
cpu_to_be64s(&on_disk_reftable[refblock_index]);
403
}
404
405
- ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset,
406
- reftable_size * REFTABLE_ENTRY_SIZE,
407
+ ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length,
408
false);
409
if (ret < 0) {
410
fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
411
goto fail;
412
}
413
414
- assert(reftable_size < INT_MAX / REFTABLE_ENTRY_SIZE);
415
+ assert(reftable_length < INT_MAX);
416
ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,
417
- reftable_size * REFTABLE_ENTRY_SIZE);
418
+ reftable_length);
419
if (ret < 0) {
420
fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
421
goto fail;
422
@@ -XXX,XX +XXX,XX @@ write_refblocks:
423
/* Enter new reftable into the image header */
424
reftable_offset_and_clusters.reftable_offset = cpu_to_be64(reftable_offset);
425
reftable_offset_and_clusters.reftable_clusters =
426
- cpu_to_be32(size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE));
427
+ cpu_to_be32(reftable_clusters);
428
ret = bdrv_pwrite_sync(bs->file,
429
offsetof(QCowHeader, refcount_table_offset),
430
&reftable_offset_and_clusters,
431
@@ -XXX,XX +XXX,XX @@ write_refblocks:
432
goto fail;
433
}
434
435
- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {
436
+ for (refblock_index = 0; refblock_index < on_disk_reftable_entries;
437
+ refblock_index++)
438
+ {
439
be64_to_cpus(&on_disk_reftable[refblock_index]);
440
}
441
s->refcount_table = on_disk_reftable;
442
s->refcount_table_offset = reftable_offset;
443
- s->refcount_table_size = reftable_size;
444
+ s->refcount_table_size = on_disk_reftable_entries;
445
update_max_refcount_table_index(s);
446
447
return 0;
1223
return 0;
1224
}
1225
1226
-#endif /* !HAS_LIBSSH2_SFTP_FSYNC */
1227
+#endif /* !HAVE_LIBSSH_0_8 */
1228
1229
static int64_t ssh_getlength(BlockDriverState *bs)
1230
{
1231
BDRVSSHState *s = bs->opaque;
1232
int64_t length;
1233
1234
- /* Note we cannot make a libssh2 call here. */
1235
- length = (int64_t) s->attrs.filesize;
1236
+ /* Note we cannot make a libssh call here. */
1237
+ length = (int64_t) s->attrs->size;
1238
trace_ssh_getlength(length);
1239
1240
return length;
1241
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn ssh_co_truncate(BlockDriverState *bs, int64_t offset,
1242
return -ENOTSUP;
1243
}
1244
1245
- if (offset < s->attrs.filesize) {
1246
+ if (offset < s->attrs->size) {
1247
error_setg(errp, "ssh driver does not support shrinking files");
1248
return -ENOTSUP;
1249
}
1250
1251
- if (offset == s->attrs.filesize) {
1252
+ if (offset == s->attrs->size) {
1253
return 0;
1254
}
1255
1256
@@ -XXX,XX +XXX,XX @@ static void bdrv_ssh_init(void)
1257
{
1258
int r;
1259
1260
- r = libssh2_init(0);
1261
+ r = ssh_init();
1262
if (r != 0) {
1263
- fprintf(stderr, "libssh2 initialization failed, %d\n", r);
1264
+ fprintf(stderr, "libssh initialization failed, %d\n", r);
1265
exit(EXIT_FAILURE);
1266
}
1267
1268
+#if TRACE_LIBSSH != 0
1269
+ ssh_set_log_level(TRACE_LIBSSH);
1270
+#endif
1271
+
1272
bdrv_register(&bdrv_ssh);
1273
}
1274
1275
diff --git a/.travis.yml b/.travis.yml
1276
index XXXXXXX..XXXXXXX 100644
1277
--- a/.travis.yml
1278
+++ b/.travis.yml
1279
@@ -XXX,XX +XXX,XX @@ addons:
1280
- libseccomp-dev
1281
- libspice-protocol-dev
1282
- libspice-server-dev
1283
- - libssh2-1-dev
1284
+ - libssh-dev
1285
- liburcu-dev
1286
- libusb-1.0-0-dev
1287
- libvte-2.91-dev
1288
@@ -XXX,XX +XXX,XX @@ matrix:
1289
- libseccomp-dev
1290
- libspice-protocol-dev
1291
- libspice-server-dev
1292
- - libssh2-1-dev
1293
+ - libssh-dev
1294
- liburcu-dev
1295
- libusb-1.0-0-dev
1296
- libvte-2.91-dev
1297
diff --git a/block/trace-events b/block/trace-events
1298
index XXXXXXX..XXXXXXX 100644
1299
--- a/block/trace-events
1300
+++ b/block/trace-events
1301
@@ -XXX,XX +XXX,XX @@ nbd_client_connect_success(const char *export_name) "export '%s'"
1302
# ssh.c
1303
ssh_restart_coroutine(void *co) "co=%p"
1304
ssh_flush(void) "fsync"
1305
-ssh_check_host_key_knownhosts(const char *key) "host key OK: %s"
1306
+ssh_check_host_key_knownhosts(void) "host key OK"
1307
ssh_connect_to_ssh(char *path, int flags, int mode) "opening file %s flags=0x%x creat_mode=0%o"
1308
ssh_co_yield(int sock, void *rd_handler, void *wr_handler) "s->sock=%d rd_handler=%p wr_handler=%p"
1309
ssh_co_yield_back(int sock) "s->sock=%d - back"
1310
ssh_getlength(int64_t length) "length=%" PRIi64
1311
ssh_co_create_opts(uint64_t size) "total_size=%" PRIu64
1312
ssh_read(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu"
1313
-ssh_read_buf(void *buf, size_t size) "sftp_read buf=%p size=%zu"
1314
-ssh_read_return(ssize_t ret) "sftp_read returned %zd"
1315
+ssh_read_buf(void *buf, size_t size, size_t actual_size) "sftp_read buf=%p size=%zu (actual size=%zu)"
1316
+ssh_read_return(ssize_t ret, int sftp_err) "sftp_read returned %zd (sftp error=%d)"
1317
ssh_write(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu"
1318
-ssh_write_buf(void *buf, size_t size) "sftp_write buf=%p size=%zu"
1319
-ssh_write_return(ssize_t ret) "sftp_write returned %zd"
1320
+ssh_write_buf(void *buf, size_t size, size_t actual_size) "sftp_write buf=%p size=%zu (actual size=%zu)"
1321
+ssh_write_return(ssize_t ret, int sftp_err) "sftp_write returned %zd (sftp error=%d)"
1322
ssh_seek(int64_t offset) "seeking to offset=%" PRIi64
1323
+ssh_auth_methods(int methods) "auth methods=0x%x"
1324
+ssh_server_status(int status) "server status=%d"
1325
1326
# curl.c
1327
curl_timer_cb(long timeout_ms) "timer callback timeout_ms %ld"
1328
@@ -XXX,XX +XXX,XX @@ sheepdog_snapshot_create(const char *sn_name, const char *id) "%s %s"
1329
sheepdog_snapshot_create_inode(const char *name, uint32_t snap, uint32_t vdi) "s->inode: name %s snap_id 0x%" PRIx32 " vdi 0x%" PRIx32
1330
1331
# ssh.c
1332
-sftp_error(const char *op, const char *ssh_err, int ssh_err_code, unsigned long sftp_err_code) "%s failed: %s (libssh2 error code: %d, sftp error code: %lu)"
1333
+sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)"
1334
diff --git a/docs/qemu-block-drivers.texi b/docs/qemu-block-drivers.texi
1335
index XXXXXXX..XXXXXXX 100644
1336
--- a/docs/qemu-block-drivers.texi
1337
+++ b/docs/qemu-block-drivers.texi
1338
@@ -XXX,XX +XXX,XX @@ print a warning when @code{fsync} is not supported:
1339
1340
warning: ssh server @code{ssh.example.com:22} does not support fsync
1341
1342
-With sufficiently new versions of libssh2 and OpenSSH, @code{fsync} is
1343
+With sufficiently new versions of libssh and OpenSSH, @code{fsync} is
1344
supported.
1345
1346
@node disk_images_nvme
1347
diff --git a/tests/docker/dockerfiles/debian-win32-cross.docker b/tests/docker/dockerfiles/debian-win32-cross.docker
1348
index XXXXXXX..XXXXXXX 100644
1349
--- a/tests/docker/dockerfiles/debian-win32-cross.docker
1350
+++ b/tests/docker/dockerfiles/debian-win32-cross.docker
1351
@@ -XXX,XX +XXX,XX @@ RUN DEBIAN_FRONTEND=noninteractive eatmydata \
1352
mxe-$TARGET-w64-mingw32.shared-curl \
1353
mxe-$TARGET-w64-mingw32.shared-glib \
1354
mxe-$TARGET-w64-mingw32.shared-libgcrypt \
1355
- mxe-$TARGET-w64-mingw32.shared-libssh2 \
1356
mxe-$TARGET-w64-mingw32.shared-libusb1 \
1357
mxe-$TARGET-w64-mingw32.shared-lzo \
1358
mxe-$TARGET-w64-mingw32.shared-nettle \
1359
diff --git a/tests/docker/dockerfiles/debian-win64-cross.docker b/tests/docker/dockerfiles/debian-win64-cross.docker
1360
index XXXXXXX..XXXXXXX 100644
1361
--- a/tests/docker/dockerfiles/debian-win64-cross.docker
1362
+++ b/tests/docker/dockerfiles/debian-win64-cross.docker
1363
@@ -XXX,XX +XXX,XX @@ RUN DEBIAN_FRONTEND=noninteractive eatmydata \
1364
mxe-$TARGET-w64-mingw32.shared-curl \
1365
mxe-$TARGET-w64-mingw32.shared-glib \
1366
mxe-$TARGET-w64-mingw32.shared-libgcrypt \
1367
- mxe-$TARGET-w64-mingw32.shared-libssh2 \
1368
mxe-$TARGET-w64-mingw32.shared-libusb1 \
1369
mxe-$TARGET-w64-mingw32.shared-lzo \
1370
mxe-$TARGET-w64-mingw32.shared-nettle \
1371
diff --git a/tests/docker/dockerfiles/fedora.docker b/tests/docker/dockerfiles/fedora.docker
1372
index XXXXXXX..XXXXXXX 100644
1373
--- a/tests/docker/dockerfiles/fedora.docker
1374
+++ b/tests/docker/dockerfiles/fedora.docker
1375
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES \
1376
libpng-devel \
1377
librbd-devel \
1378
libseccomp-devel \
1379
- libssh2-devel \
1380
+ libssh-devel \
1381
libubsan \
1382
libusbx-devel \
1383
libxml2-devel \
1384
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES \
1385
mingw32-gtk3 \
1386
mingw32-libjpeg-turbo \
1387
mingw32-libpng \
1388
- mingw32-libssh2 \
1389
mingw32-libtasn1 \
1390
mingw32-nettle \
1391
mingw32-pixman \
1392
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES \
1393
mingw64-gtk3 \
1394
mingw64-libjpeg-turbo \
1395
mingw64-libpng \
1396
- mingw64-libssh2 \
1397
mingw64-libtasn1 \
1398
mingw64-nettle \
1399
mingw64-pixman \
1400
diff --git a/tests/docker/dockerfiles/ubuntu.docker b/tests/docker/dockerfiles/ubuntu.docker
1401
index XXXXXXX..XXXXXXX 100644
1402
--- a/tests/docker/dockerfiles/ubuntu.docker
1403
+++ b/tests/docker/dockerfiles/ubuntu.docker
1404
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES flex bison \
1405
libsnappy-dev \
1406
libspice-protocol-dev \
1407
libspice-server-dev \
1408
- libssh2-1-dev \
1409
+ libssh-dev \
1410
libusb-1.0-0-dev \
1411
libusbredirhost-dev \
1412
libvdeplug-dev \
1413
diff --git a/tests/docker/dockerfiles/ubuntu1804.docker b/tests/docker/dockerfiles/ubuntu1804.docker
1414
index XXXXXXX..XXXXXXX 100644
1415
--- a/tests/docker/dockerfiles/ubuntu1804.docker
1416
+++ b/tests/docker/dockerfiles/ubuntu1804.docker
1417
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES flex bison \
1418
libsnappy-dev \
1419
libspice-protocol-dev \
1420
libspice-server-dev \
1421
- libssh2-1-dev \
1422
+ libssh-dev \
1423
libusb-1.0-0-dev \
1424
libusbredirhost-dev \
1425
libvdeplug-dev \
1426
diff --git a/tests/qemu-iotests/207 b/tests/qemu-iotests/207
1427
index XXXXXXX..XXXXXXX 100755
1428
--- a/tests/qemu-iotests/207
1429
+++ b/tests/qemu-iotests/207
1430
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1431
1432
iotests.img_info_log(remote_path)
1433
1434
- md5_key = subprocess.check_output(
1435
- 'ssh-keyscan -t rsa 127.0.0.1 2>/dev/null | grep -v "\\^#" | ' +
1436
- 'cut -d" " -f3 | base64 -d | md5sum -b | cut -d" " -f1',
1437
- shell=True).rstrip().decode('ascii')
1438
+ keys = subprocess.check_output(
1439
+ 'ssh-keyscan 127.0.0.1 2>/dev/null | grep -v "\\^#" | ' +
1440
+ 'cut -d" " -f3',
1441
+ shell=True).rstrip().decode('ascii').split('\n')
1442
+
1443
+ # Mappings of base64 representations to digests
1444
+ md5_keys = {}
1445
+ sha1_keys = {}
1446
+
1447
+ for key in keys:
1448
+ md5_keys[key] = subprocess.check_output(
1449
+ 'echo %s | base64 -d | md5sum -b | cut -d" " -f1' % key,
1450
+ shell=True).rstrip().decode('ascii')
1451
+
1452
+ sha1_keys[key] = subprocess.check_output(
1453
+ 'echo %s | base64 -d | sha1sum -b | cut -d" " -f1' % key,
1454
+ shell=True).rstrip().decode('ascii')
1455
1456
vm.launch()
1457
+
1458
+ # Find correct key first
1459
+ matching_key = None
1460
+ for key in keys:
1461
+ result = vm.qmp('blockdev-add',
1462
+ driver='ssh', node_name='node0', path=disk_path,
1463
+ server={
1464
+ 'host': '127.0.0.1',
1465
+ 'port': '22',
1466
+ }, host_key_check={
1467
+ 'mode': 'hash',
1468
+ 'type': 'md5',
1469
+ 'hash': md5_keys[key],
1470
+ })
1471
+
1472
+ if 'error' not in result:
1473
+ vm.qmp('blockdev-del', node_name='node0')
1474
+ matching_key = key
1475
+ break
1476
+
1477
+ if matching_key is None:
1478
+ vm.shutdown()
1479
+ iotests.notrun('Did not find a key that fits 127.0.0.1')
1480
+
1481
blockdev_create(vm, { 'driver': 'ssh',
1482
'location': {
1483
'path': disk_path,
1484
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1485
'host-key-check': {
1486
'mode': 'hash',
1487
'type': 'md5',
1488
- 'hash': md5_key,
1489
+ 'hash': md5_keys[matching_key],
1490
}
1491
},
1492
'size': 8388608 })
1493
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1494
1495
iotests.img_info_log(remote_path)
1496
1497
- sha1_key = subprocess.check_output(
1498
- 'ssh-keyscan -t rsa 127.0.0.1 2>/dev/null | grep -v "\\^#" | ' +
1499
- 'cut -d" " -f3 | base64 -d | sha1sum -b | cut -d" " -f1',
1500
- shell=True).rstrip().decode('ascii')
1501
-
1502
vm.launch()
1503
blockdev_create(vm, { 'driver': 'ssh',
1504
'location': {
1505
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1506
'host-key-check': {
1507
'mode': 'hash',
1508
'type': 'sha1',
1509
- 'hash': sha1_key,
1510
+ 'hash': sha1_keys[matching_key],
1511
}
1512
},
1513
'size': 4194304 })
1514
diff --git a/tests/qemu-iotests/207.out b/tests/qemu-iotests/207.out
1515
index XXXXXXX..XXXXXXX 100644
1516
--- a/tests/qemu-iotests/207.out
1517
+++ b/tests/qemu-iotests/207.out
1518
@@ -XXX,XX +XXX,XX @@ virtual size: 4 MiB (4194304 bytes)
1519
1520
{"execute": "blockdev-create", "arguments": {"job-id": "job0", "options": {"driver": "ssh", "location": {"host-key-check": {"mode": "none"}, "path": "/this/is/not/an/existing/path", "server": {"host": "127.0.0.1", "port": "22"}}, "size": 4194304}}}
1521
{"return": {}}
1522
-Job failed: failed to open remote file '/this/is/not/an/existing/path': Failed opening remote file (libssh2 error code: -31)
1523
+Job failed: failed to open remote file '/this/is/not/an/existing/path': SFTP server: No such file (libssh error code: 1, sftp error code: 2)
1524
{"execute": "job-dismiss", "arguments": {"id": "job0"}}
1525
{"return": {}}
1526
448
--
1527
--
449
2.35.1
1528
2.21.0
1529
1530
diff view generated by jsdifflib
1
Instead of fprint()-ing error messages in rebuild_refcount_structure()
1
Tests should place their files into the test directory. This includes
2
and its rebuild_refcounts_write_refblocks() helper, pass them through an
2
Unix sockets. 205 currently fails to do so, which prevents it from
3
Error object to qcow2_check_refcounts() (which will then print it).
3
being run concurrently.
4
4
5
Suggested-by: Eric Blake <eblake@redhat.com>
5
Signed-off-by: Max Reitz <mreitz@redhat.com>
6
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
6
Message-id: 20190618210238.9524-1-mreitz@redhat.com
7
Message-Id: <20220405134652.19278-4-hreitz@redhat.com>
8
Reviewed-by: Eric Blake <eblake@redhat.com>
7
Reviewed-by: Eric Blake <eblake@redhat.com>
8
Signed-off-by: Max Reitz <mreitz@redhat.com>
9
---
9
---
10
block/qcow2-refcount.c | 33 +++++++++++++++++++--------------
10
tests/qemu-iotests/205 | 2 +-
11
1 file changed, 19 insertions(+), 14 deletions(-)
11
1 file changed, 1 insertion(+), 1 deletion(-)
12
12
13
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
13
diff --git a/tests/qemu-iotests/205 b/tests/qemu-iotests/205
14
index XXXXXXX..XXXXXXX 100644
14
index XXXXXXX..XXXXXXX 100755
15
--- a/block/qcow2-refcount.c
15
--- a/tests/qemu-iotests/205
16
+++ b/block/qcow2-refcount.c
16
+++ b/tests/qemu-iotests/205
17
@@ -XXX,XX +XXX,XX @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs,
17
@@ -XXX,XX +XXX,XX @@ import iotests
18
static int rebuild_refcounts_write_refblocks(
18
import time
19
BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters,
19
from iotests import qemu_img_create, qemu_io, filter_qemu_io, QemuIoInteractive
20
int64_t first_cluster, int64_t end_cluster,
20
21
- uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr
21
-nbd_sock = 'nbd_sock'
22
+ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr,
22
+nbd_sock = os.path.join(iotests.test_dir, 'nbd_sock')
23
+ Error **errp
23
nbd_uri = 'nbd+unix:///exp?socket=' + nbd_sock
24
)
24
disk = os.path.join(iotests.test_dir, 'disk')
25
{
26
BDRVQcow2State *s = bs->opaque;
27
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks(
28
nb_clusters,
29
&first_free_cluster);
30
if (refblock_offset < 0) {
31
- fprintf(stderr, "ERROR allocating refblock: %s\n",
32
- strerror(-refblock_offset));
33
+ error_setg_errno(errp, -refblock_offset,
34
+ "ERROR allocating refblock");
35
return refblock_offset;
36
}
37
38
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks(
39
on_disk_reftable_entries *
40
REFTABLE_ENTRY_SIZE);
41
if (!on_disk_reftable) {
42
+ error_setg(errp, "ERROR allocating reftable memory");
43
return -ENOMEM;
44
}
45
46
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks(
47
ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset,
48
s->cluster_size, false);
49
if (ret < 0) {
50
- fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
51
+ error_setg_errno(errp, -ret, "ERROR writing refblock");
52
return ret;
53
}
54
55
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks(
56
ret = bdrv_pwrite(bs->file, refblock_offset, on_disk_refblock,
57
s->cluster_size);
58
if (ret < 0) {
59
- fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
60
+ error_setg_errno(errp, -ret, "ERROR writing refblock");
61
return ret;
62
}
63
64
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks(
65
static int rebuild_refcount_structure(BlockDriverState *bs,
66
BdrvCheckResult *res,
67
void **refcount_table,
68
- int64_t *nb_clusters)
69
+ int64_t *nb_clusters,
70
+ Error **errp)
71
{
72
BDRVQcow2State *s = bs->opaque;
73
int64_t reftable_offset = -1;
74
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs,
75
rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,
76
0, *nb_clusters,
77
&on_disk_reftable,
78
- &on_disk_reftable_entries);
79
+ &on_disk_reftable_entries, errp);
80
if (reftable_size_changed < 0) {
81
res->check_errors++;
82
ret = reftable_size_changed;
83
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs,
84
refcount_table, nb_clusters,
85
&first_free_cluster);
86
if (reftable_offset < 0) {
87
- fprintf(stderr, "ERROR allocating reftable: %s\n",
88
- strerror(-reftable_offset));
89
+ error_setg_errno(errp, -reftable_offset,
90
+ "ERROR allocating reftable");
91
res->check_errors++;
92
ret = reftable_offset;
93
goto fail;
94
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs,
95
reftable_start_cluster,
96
reftable_end_cluster,
97
&on_disk_reftable,
98
- &on_disk_reftable_entries);
99
+ &on_disk_reftable_entries, errp);
100
if (reftable_size_changed < 0) {
101
res->check_errors++;
102
ret = reftable_size_changed;
103
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs,
104
ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length,
105
false);
106
if (ret < 0) {
107
- fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
108
+ error_setg_errno(errp, -ret, "ERROR writing reftable");
109
goto fail;
110
}
111
112
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs,
113
ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,
114
reftable_length);
115
if (ret < 0) {
116
- fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
117
+ error_setg_errno(errp, -ret, "ERROR writing reftable");
118
goto fail;
119
}
120
121
@@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs,
122
&reftable_offset_and_clusters,
123
sizeof(reftable_offset_and_clusters));
124
if (ret < 0) {
125
- fprintf(stderr, "ERROR setting reftable: %s\n", strerror(-ret));
126
+ error_setg_errno(errp, -ret, "ERROR setting reftable");
127
goto fail;
128
}
129
130
@@ -XXX,XX +XXX,XX @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
131
if (rebuild && (fix & BDRV_FIX_ERRORS)) {
132
BdrvCheckResult old_res = *res;
133
int fresh_leaks = 0;
134
+ Error *local_err = NULL;
135
136
fprintf(stderr, "Rebuilding refcount structure\n");
137
ret = rebuild_refcount_structure(bs, res, &refcount_table,
138
- &nb_clusters);
139
+ &nb_clusters, &local_err);
140
if (ret < 0) {
141
+ error_report_err(local_err);
142
goto fail;
143
}
144
25
145
--
26
--
146
2.35.1
27
2.21.0
28
29
diff view generated by jsdifflib