The following changes since commit 804b30d25f8d70dc2dea951883ea92235274a50c: Merge remote-tracking branch 'remotes/legoater/tags/pull-ppc-20220130' into staging (2022-01-31 11:10:08 +0000) are available in the Git repository at: https://gitlab.com/hreitz/qemu.git tags/pull-block-2022-02-01 for you to fetch changes up to 751486c18555169ca4baf59440275d5831140822: block.h: remove outdated comment (2022-02-01 13:28:53 +0100) ---------------------------------------------------------------- Block patches: - Add support to the iotests to test qcow2's zstd compression mode - Fix post-migration block node permissions - iotests fixes (051 and mirror-ready-cancel-error) - Remove an outdated comment ---------------------------------------------------------------- Emanuele Giuseppe Esposito (1): block.h: remove outdated comment Hanna Reitz (3): iotests/MRCE: Write data to source block-backend: Retain permissions after migration iotests/migration-permissions: New test Thomas Huth (1): tests/qemu-iotests: Fix 051 for binaries without 'lsi53c895a' Vladimir Sementsov-Ogievskiy (19): iotests.py: img_info_log(): rename imgopts argument iotests.py: implement unsupported_imgopts iotests: specify some unsupported_imgopts for python iotests iotests.py: qemu_img*("create"): support IMGOPTS='compression_type=zstd' iotests: drop qemu_img_verbose() helper iotests.py: rewrite default luks support in qemu_img iotest 303: explicit compression type iotest 065: explicit compression type iotests.py: filter out successful output of qemu-img create iotests.py: filter compression type out iotest 302: use img_info_log() helper qcow2: simple case support for downgrading of qcow2 images with zstd iotests/common.rc: introduce _qcow2_dump_header helper iotests: massive use _qcow2_dump_header iotest 39: use _qcow2_dump_header iotests: bash tests: filter compression type iotests 60: more accurate set dirty bit in qcow2 header iotest 214: explicit compression type iotests: declare lack of support for compresion_type in IMGOPTS include/block/block.h | 1 - block/block-backend.c | 11 ++ block/qcow2.c | 58 +++++++++- tests/qemu-iotests/031 | 11 +- tests/qemu-iotests/036 | 6 +- tests/qemu-iotests/039 | 22 ++-- tests/qemu-iotests/044 | 8 +- tests/qemu-iotests/044.out | 1 + tests/qemu-iotests/051 | 9 +- tests/qemu-iotests/060 | 22 ++-- tests/qemu-iotests/060.out | 2 +- tests/qemu-iotests/061 | 42 ++++---- tests/qemu-iotests/061.out | 12 +-- tests/qemu-iotests/065 | 19 ++-- tests/qemu-iotests/082.out | 14 +-- tests/qemu-iotests/112 | 3 +- tests/qemu-iotests/137 | 2 +- tests/qemu-iotests/149.out | 21 ---- tests/qemu-iotests/163 | 3 +- tests/qemu-iotests/165 | 3 +- tests/qemu-iotests/196 | 3 +- tests/qemu-iotests/198.out | 4 +- tests/qemu-iotests/206.out | 10 +- tests/qemu-iotests/209 | 7 +- tests/qemu-iotests/209.out | 2 + tests/qemu-iotests/210 | 8 +- tests/qemu-iotests/214 | 2 +- tests/qemu-iotests/237.out | 3 - tests/qemu-iotests/242 | 3 +- tests/qemu-iotests/242.out | 10 +- tests/qemu-iotests/246 | 3 +- tests/qemu-iotests/254 | 3 +- tests/qemu-iotests/255.out | 4 - tests/qemu-iotests/260 | 3 +- tests/qemu-iotests/274 | 3 +- tests/qemu-iotests/274.out | 39 +------ tests/qemu-iotests/280.out | 1 - tests/qemu-iotests/281 | 3 +- tests/qemu-iotests/287 | 8 +- tests/qemu-iotests/290 | 2 +- tests/qemu-iotests/296.out | 10 +- tests/qemu-iotests/302 | 4 +- tests/qemu-iotests/302.out | 7 +- tests/qemu-iotests/303 | 26 +++-- tests/qemu-iotests/303.out | 30 +++++- tests/qemu-iotests/common.filter | 8 ++ tests/qemu-iotests/common.rc | 22 ++++ tests/qemu-iotests/iotests.py | 99 +++++++++++------ .../tests/migrate-bitmaps-postcopy-test | 3 +- tests/qemu-iotests/tests/migrate-bitmaps-test | 3 +- .../qemu-iotests/tests/migration-permissions | 101 ++++++++++++++++++ .../tests/migration-permissions.out | 5 + .../tests/mirror-ready-cancel-error | 7 +- .../tests/remove-bitmap-from-backing | 3 +- 54 files changed, 483 insertions(+), 236 deletions(-) create mode 100755 tests/qemu-iotests/tests/migration-permissions create mode 100644 tests/qemu-iotests/tests/migration-permissions.out -- 2.34.1 From: Thomas Huth <thuth@redhat.com> The lsi53c895a SCSI adaptor might not be enabled in each and every x86 QEMU binary, e.g. it's disabled in the RHEL/CentOS build. Thus let's add a check to the 051 test so that it does not fail if this device is not available. Signed-off-by: Thomas Huth <thuth@redhat.com> Message-Id: <20211206143404.247032-1-thuth@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/051 | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/051 +++ b/tests/qemu-iotests/051 @@ -XXX,XX +XXX,XX @@ _supported_proto file _unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file _require_drivers nbd +if [ "$QEMU_DEFAULT_MACHINE" = "pc" ]; then + _require_devices lsi53c895a +fi + do_run_qemu() { echo Testing: "$@" -- 2.34.1 This test assumes that mirror flushes the source when entering the READY state, and that the format level will pass that flush on to the protocol level (where we intercept it with blkdebug). However, apparently that does not happen when using a VMDK image with zeroed_grain=on, which actually is the default set by testenv.py. Right now, Python tests ignore IMGOPTS, though, so this has no effect; but Vladimir has a series that will change this, so we need to fix this test before that series lands. We can fix it by writing data to the source before we start the mirror job; apparently that makes the (VMDK) format layer change its mind and pass on the pre-READY flush to the protocol level, so the test passes again. (I presume, without any data written, mirror just does a 64M zero write on the target, which VMDK with zeroed_grain=on basically just ignores.) Without this, we do not get a flush, and so blkdebug only sees a single flush at the end of the job instead of two, and therefore does not inject an error, which makes the block job complete instead of raising an error. Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223165308.103793-1-hreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> --- tests/qemu-iotests/tests/mirror-ready-cancel-error | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/tests/mirror-ready-cancel-error b/tests/qemu-iotests/tests/mirror-ready-cancel-error index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/tests/mirror-ready-cancel-error +++ b/tests/qemu-iotests/tests/mirror-ready-cancel-error @@ -XXX,XX +XXX,XX @@ class TestMirrorReadyCancelError(iotests.QMPTestCase): assert iotests.qemu_img_create('-f', iotests.imgfmt, target, str(image_size)) == 0 + # Ensure that mirror will copy something before READY so the + # target format layer will forward the pre-READY flush to its + # file child + assert iotests.qemu_io_silent('-c', 'write -P 1 0 64k', source) == 0 + self.vm = iotests.VM() self.vm.launch() @@ -XXX,XX +XXX,XX @@ class TestMirrorReadyCancelError(iotests.QMPTestCase): # Write something so will not leave the job immediately, but # flush first (which will fail, thanks to blkdebug) res = self.vm.qmp('human-monitor-command', - command_line='qemu-io mirror-top "write 0 64k"') + command_line='qemu-io mirror-top "write -P 2 0 64k"') self.assert_qmp(res, 'return', '') # Drain status change events -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to support IMGOPTS environment variable like in bash tests. Corresponding global variable in iotests.py should be called imgopts. So to not interfere with function argument, rename it in advance. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-2-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/210 | 8 ++++---- tests/qemu-iotests/iotests.py | 5 +++-- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/tests/qemu-iotests/210 b/tests/qemu-iotests/210 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/210 +++ b/tests/qemu-iotests/210 @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.luks') as disk_path, \ 'driver=luks,file.driver=file,file.filename=%s,key-secret=keysec0' % (disk_path), filter_path=disk_path, extra_args=['--object', 'secret,id=keysec0,data=foo'], - imgopts=True) + use_image_opts=True) # # Successful image creation (with non-default options) @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.luks') as disk_path, \ 'driver=luks,file.driver=file,file.filename=%s,key-secret=keysec0' % (disk_path), filter_path=disk_path, extra_args=['--object', 'secret,id=keysec0,data=foo'], - imgopts=True) + use_image_opts=True) # # Invalid BlockdevRef @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.luks') as disk_path, \ 'driver=luks,file.driver=file,file.filename=%s,key-secret=keysec0' % (disk_path), filter_path=disk_path, extra_args=['--object', 'secret,id=keysec0,data=foo'], - imgopts=True) + use_image_opts=True) # # Invalid sizes @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.luks') as disk_path, \ 'driver=luks,file.driver=file,file.filename=%s,key-secret=keysec0' % (disk_path), filter_path=disk_path, extra_args=['--object', 'secret,id=keysec0,data=foo'], - imgopts=True) + use_image_opts=True) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def qemu_img_log(*args): log(result, filters=[filter_testfiles]) return result -def img_info_log(filename, filter_path=None, imgopts=False, extra_args=()): +def img_info_log(filename, filter_path=None, use_image_opts=False, + extra_args=()): args = ['info'] - if imgopts: + if use_image_opts: args.append('--image-opts') else: args += ['-f', imgfmt] -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to support some addition IMGOPTS in python iotests like in bash iotests. Similarly to bash iotests, we want a way to skip some tests which can't work with specific IMGOPTS. Globally for python iotests we will not support things like 'data_file=$TEST_IMG.ext_data_file' in IMGOPTS, so, forbid this globally in iotests.py. Suggested-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-3-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def _verify_virtio_scsi_pci_or_ccw() -> None: notrun('Missing virtio-scsi-pci or virtio-scsi-ccw in QEMU binary') +def _verify_imgopts(unsupported: Sequence[str] = ()) -> None: + imgopts = os.environ.get('IMGOPTS') + # One of usage examples for IMGOPTS is "data_file=$TEST_IMG.ext_data_file" + # but it supported only for bash tests. We don't have a concept of global + # TEST_IMG in iotests.py, not saying about somehow parsing $variables. + # So, for simplicity let's just not support any IMGOPTS with '$' inside. + unsup = list(unsupported) + ['$'] + if imgopts and any(x in imgopts for x in unsup): + notrun(f'not suitable for this imgopts: {imgopts}') + + def supports_quorum(): return 'quorum' in qemu_img_pipe('--help') @@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (), unsupported_fmts: Sequence[str] = (), supported_protocols: Sequence[str] = (), unsupported_protocols: Sequence[str] = (), - required_fmts: Sequence[str] = ()) -> bool: + required_fmts: Sequence[str] = (), + unsupported_imgopts: Sequence[str] = ()) -> bool: """ Perform necessary setup for either script-style or unittest-style tests. @@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (), _verify_aio_mode(supported_aio_modes) _verify_formats(required_fmts) _verify_virtio_blk() + _verify_imgopts(unsupported_imgopts) return debug -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to support IMGOPTS for python iotests. Still some iotests will not work with common IMGOPTS used with bash iotests like specifying refcount_bits and compat qcow2 options. So we should define corresponding unsupported_imgopts for now. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20211223160144.1097696-4-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/044 | 3 ++- tests/qemu-iotests/065 | 3 ++- tests/qemu-iotests/163 | 3 ++- tests/qemu-iotests/165 | 3 ++- tests/qemu-iotests/196 | 3 ++- tests/qemu-iotests/242 | 3 ++- tests/qemu-iotests/246 | 3 ++- tests/qemu-iotests/254 | 3 ++- tests/qemu-iotests/260 | 3 ++- tests/qemu-iotests/274 | 3 ++- tests/qemu-iotests/281 | 3 ++- tests/qemu-iotests/303 | 3 ++- tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test | 3 ++- tests/qemu-iotests/tests/migrate-bitmaps-test | 3 ++- tests/qemu-iotests/tests/remove-bitmap-from-backing | 3 ++- 15 files changed, 30 insertions(+), 15 deletions(-) diff --git a/tests/qemu-iotests/044 b/tests/qemu-iotests/044 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/044 +++ b/tests/qemu-iotests/044 @@ -XXX,XX +XXX,XX @@ class TestRefcountTableGrowth(iotests.QMPTestCase): if __name__ == '__main__': iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['refcount_bits']) diff --git a/tests/qemu-iotests/065 b/tests/qemu-iotests/065 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/065 +++ b/tests/qemu-iotests/065 @@ -XXX,XX +XXX,XX @@ TestQMP = None if __name__ == '__main__': iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['refcount_bits']) diff --git a/tests/qemu-iotests/163 b/tests/qemu-iotests/163 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/163 +++ b/tests/qemu-iotests/163 @@ -XXX,XX +XXX,XX @@ ShrinkBaseClass = None if __name__ == '__main__': iotests.main(supported_fmts=['raw', 'qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['compat']) diff --git a/tests/qemu-iotests/165 b/tests/qemu-iotests/165 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/165 +++ b/tests/qemu-iotests/165 @@ -XXX,XX +XXX,XX @@ class TestPersistentDirtyBitmap(iotests.QMPTestCase): if __name__ == '__main__': iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['compat']) diff --git a/tests/qemu-iotests/196 b/tests/qemu-iotests/196 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/196 +++ b/tests/qemu-iotests/196 @@ -XXX,XX +XXX,XX @@ class TestInvalidateAutoclear(iotests.QMPTestCase): if __name__ == '__main__': iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['compat']) diff --git a/tests/qemu-iotests/242 b/tests/qemu-iotests/242 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/242 +++ b/tests/qemu-iotests/242 @@ -XXX,XX +XXX,XX @@ from iotests import qemu_img_create, qemu_io, qemu_img_pipe, \ file_path, img_info_log, log, filter_qemu_io iotests.script_initialize(supported_fmts=['qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['refcount_bits', 'compat']) disk = file_path('disk') chunk = 256 * 1024 diff --git a/tests/qemu-iotests/246 b/tests/qemu-iotests/246 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/246 +++ b/tests/qemu-iotests/246 @@ -XXX,XX +XXX,XX @@ import iotests from iotests import log -iotests.script_initialize(supported_fmts=['qcow2']) +iotests.script_initialize(supported_fmts=['qcow2'], + unsupported_imgopts=['compat']) size = 64 * 1024 * 1024 * 1024 gran_small = 32 * 1024 gran_large = 128 * 1024 diff --git a/tests/qemu-iotests/254 b/tests/qemu-iotests/254 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/254 +++ b/tests/qemu-iotests/254 @@ -XXX,XX +XXX,XX @@ import iotests from iotests import qemu_img_create, file_path, log -iotests.script_initialize(supported_fmts=['qcow2']) +iotests.script_initialize(supported_fmts=['qcow2'], + unsupported_imgopts=['compat']) disk, top = file_path('disk', 'top') size = 1024 * 1024 diff --git a/tests/qemu-iotests/260 b/tests/qemu-iotests/260 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/260 +++ b/tests/qemu-iotests/260 @@ -XXX,XX +XXX,XX @@ import iotests from iotests import qemu_img_create, file_path, log, filter_qmp_event iotests.script_initialize( - supported_fmts=['qcow2'] + supported_fmts=['qcow2'], + unsupported_imgopts=['compat'] ) base, top = file_path('base', 'top') diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/274 +++ b/tests/qemu-iotests/274 @@ -XXX,XX +XXX,XX @@ import iotests iotests.script_initialize(supported_fmts=['qcow2'], - supported_platforms=['linux']) + supported_platforms=['linux'], + unsupported_imgopts=['refcount_bits', 'compat']) size_short = 1 * 1024 * 1024 size_long = 2 * 1024 * 1024 diff --git a/tests/qemu-iotests/281 b/tests/qemu-iotests/281 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/281 +++ b/tests/qemu-iotests/281 @@ -XXX,XX +XXX,XX @@ class TestBlockdevBackupAbort(iotests.QMPTestCase): if __name__ == '__main__': iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) + supported_protocols=['file'], + unsupported_imgopts=['compat']) diff --git a/tests/qemu-iotests/303 b/tests/qemu-iotests/303 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/303 +++ b/tests/qemu-iotests/303 @@ -XXX,XX +XXX,XX @@ import iotests import subprocess from iotests import qemu_img_create, qemu_io, file_path, log, filter_qemu_io -iotests.script_initialize(supported_fmts=['qcow2']) +iotests.script_initialize(supported_fmts=['qcow2'], + unsupported_imgopts=['refcount_bits', 'compat']) disk = file_path('disk') chunk = 1024 * 1024 diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test b/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test @@ -XXX,XX +XXX,XX @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): if __name__ == '__main__': - iotests.main(supported_fmts=['qcow2']) + iotests.main(supported_fmts=['qcow2'], + unsupported_imgopts=['compat']) diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-test b/tests/qemu-iotests/tests/migrate-bitmaps-test index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-test @@ -XXX,XX +XXX,XX @@ def main() -> None: iotests.main( supported_fmts=['qcow2'], - supported_protocols=['file'] + supported_protocols=['file'], + unsupported_imgopts=['compat'] ) diff --git a/tests/qemu-iotests/tests/remove-bitmap-from-backing b/tests/qemu-iotests/tests/remove-bitmap-from-backing index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/tests/remove-bitmap-from-backing +++ b/tests/qemu-iotests/tests/remove-bitmap-from-backing @@ -XXX,XX +XXX,XX @@ import iotests from iotests import log, qemu_img_create, qemu_img, qemu_img_pipe -iotests.script_initialize(supported_fmts=['qcow2']) +iotests.script_initialize(supported_fmts=['qcow2'], + unsupported_imgopts=['compat']) top, base = iotests.file_path('top', 'base') size = '1M' -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Adding support of IMGOPTS (like in bash tests) allows user to pass a lot of different options. Still, some may require additional logic. Now we want compression_type option, so add some smart logic around it: ignore compression_type=zstd in IMGOPTS, if test want qcow2 in compatibility mode. As well, ignore compression_type for non-qcow2 formats. Note that we may instead add support only to qemu_img_create(), but that works bad: 1. We'll have to update a lot of tests to use qemu_img_create instead of qemu_img('create'). (still, we may want do it anyway, but no reason to create a dependancy between task of supporting IMGOPTS and updating a lot of tests) 2. Some tests use qemu_img_pipe('create', ..) - even more work on updating 3. Even if we update all tests to go through qemu_img_create, we'll need a way to avoid creating new tests using qemu_img*('create') - add assertions.. That doesn't seem good. So, let's add support of IMGOPTS to most generic qemu_img_pipe_and_status(). Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-5-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ # along with this program. If not, see <http://www.gnu.org/licenses/>. # +import argparse import atexit import bz2 from collections import OrderedDict @@ -XXX,XX +XXX,XX @@ def qemu_tool_pipe_and_status(tool: str, args: Sequence[str], {-subp.returncode}: {cmd}\n') return (output, subp.returncode) +def qemu_img_create_prepare_args(args: List[str]) -> List[str]: + if not args or args[0] != 'create': + return list(args) + args = args[1:] + + p = argparse.ArgumentParser(allow_abbrev=False) + p.add_argument('-f') + parsed, remaining = p.parse_known_args(args) + + result = ['create'] + if parsed.f is not None: + result += ['-f', parsed.f] + + # IMGOPTS most probably contain options specific for the selected format, + # like extended_l2 or compression_type for qcow2. Test may want to create + # additional images in other formats that doesn't support these options. + # So, use IMGOPTS only for images created in imgfmt format. + if parsed.f == imgfmt and 'IMGOPTS' in os.environ: + result += ['-o', os.environ['IMGOPTS']] + + result += remaining + + return result + def qemu_img_pipe_and_status(*args: str) -> Tuple[str, int]: """ Run qemu-img and return both its output and its exit code """ - full_args = qemu_img_args + list(args) + full_args = qemu_img_args + qemu_img_create_prepare_args(list(args)) return qemu_tool_pipe_and_status('qemu-img', full_args) def qemu_img(*args: str) -> int: -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> qemu_img_verbose() has a drawback of not going through generic qemu_img_pipe_and_status(). qemu_img_verbose() is not very popular, so update the only two users to qemu_img_log() and drop qemu_img_verbose() at all. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-6-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/044 | 5 +++-- tests/qemu-iotests/044.out | 1 + tests/qemu-iotests/209 | 7 ++++--- tests/qemu-iotests/209.out | 2 ++ tests/qemu-iotests/iotests.py | 8 -------- 5 files changed, 10 insertions(+), 13 deletions(-) diff --git a/tests/qemu-iotests/044 b/tests/qemu-iotests/044 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/044 +++ b/tests/qemu-iotests/044 @@ -XXX,XX +XXX,XX @@ import os import qcow2 from qcow2 import QcowHeader import iotests -from iotests import qemu_img, qemu_img_verbose, qemu_io +from iotests import qemu_img, qemu_img_log, qemu_io import struct import subprocess import sys @@ -XXX,XX +XXX,XX @@ class TestRefcountTableGrowth(iotests.QMPTestCase): def test_grow_refcount_table(self): qemu_io('-c', 'write 3800M 1M', test_img) - qemu_img_verbose('check' , test_img) + qemu_img_log('check' , test_img) pass if __name__ == '__main__': + iotests.activate_logging() iotests.main(supported_fmts=['qcow2'], supported_protocols=['file'], unsupported_imgopts=['refcount_bits']) diff --git a/tests/qemu-iotests/044.out b/tests/qemu-iotests/044.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/044.out +++ b/tests/qemu-iotests/044.out @@ -XXX,XX +XXX,XX @@ No errors were found on the image. 7292415/33554432 = 21.73% allocated, 0.00% fragmented, 0.00% compressed clusters Image end offset: 4296217088 + . ---------------------------------------------------------------------- Ran 1 tests diff --git a/tests/qemu-iotests/209 b/tests/qemu-iotests/209 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/209 +++ b/tests/qemu-iotests/209 @@ -XXX,XX +XXX,XX @@ # import iotests -from iotests import qemu_img_create, qemu_io, qemu_img_verbose, qemu_nbd, \ - file_path +from iotests import qemu_img_create, qemu_io, qemu_img_log, qemu_nbd, \ + file_path, log iotests.script_initialize(supported_fmts=['qcow2']) @@ -XXX,XX +XXX,XX @@ qemu_img_create('-f', iotests.imgfmt, disk, '1M') qemu_io('-f', iotests.imgfmt, '-c', 'write 0 512K', disk) qemu_nbd('-k', nbd_sock, '-x', 'exp', '-f', iotests.imgfmt, disk) -qemu_img_verbose('map', '-f', 'raw', '--output=json', nbd_uri) +qemu_img_log('map', '-f', 'raw', '--output=json', nbd_uri) +log('done.') # avoid new line at the end of output file diff --git a/tests/qemu-iotests/209.out b/tests/qemu-iotests/209.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/209.out +++ b/tests/qemu-iotests/209.out @@ -XXX,XX +XXX,XX @@ [{ "start": 0, "length": 524288, "depth": 0, "present": true, "zero": false, "data": true, "offset": 0}, { "start": 524288, "length": 524288, "depth": 0, "present": true, "zero": true, "data": false, "offset": 524288}] + +done. diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def qemu_img_measure(*args): def qemu_img_check(*args): return json.loads(qemu_img_pipe("check", "--output", "json", *args)) -def qemu_img_verbose(*args): - '''Run qemu-img without suppressing its output and return the exit code''' - exitcode = subprocess.call(qemu_img_args + list(args)) - if exitcode < 0: - sys.stderr.write('qemu-img received signal %i: %s\n' - % (-exitcode, ' '.join(qemu_img_args + list(args)))) - return exitcode - def qemu_img_pipe(*args: str) -> str: '''Run qemu-img and return its output''' return qemu_img_pipe_and_status(*args)[0] -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Move the logic to more generic qemu_img_pipe_and_status(). Also behave better when we have several -o options. And reuse argument parser of course. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-7-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 36 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 19 deletions(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def qemu_img_create_prepare_args(args: List[str]) -> List[str]: args = args[1:] p = argparse.ArgumentParser(allow_abbrev=False) + # -o option may be specified several times + p.add_argument('-o', action='append', default=[]) p.add_argument('-f') parsed, remaining = p.parse_known_args(args) + opts_list = parsed.o + result = ['create'] if parsed.f is not None: result += ['-f', parsed.f] @@ -XXX,XX +XXX,XX @@ def qemu_img_create_prepare_args(args: List[str]) -> List[str]: # like extended_l2 or compression_type for qcow2. Test may want to create # additional images in other formats that doesn't support these options. # So, use IMGOPTS only for images created in imgfmt format. - if parsed.f == imgfmt and 'IMGOPTS' in os.environ: - result += ['-o', os.environ['IMGOPTS']] + imgopts = os.environ.get('IMGOPTS') + if imgopts and parsed.f == imgfmt: + opts_list.insert(0, imgopts) + + # default luks support + if parsed.f == 'luks' and \ + all('key-secret' not in opts for opts in opts_list): + result += ['--object', luks_default_secret_object] + opts_list.append(luks_default_key_secret_opt) + + for opts in opts_list: + result += ['-o', opts] result += remaining @@ -XXX,XX +XXX,XX @@ def ordered_qmp(qmsg, conv_keys=True): return qmsg def qemu_img_create(*args): - args = list(args) - - # default luks support - if '-f' in args and args[args.index('-f') + 1] == 'luks': - if '-o' in args: - i = args.index('-o') - if 'key-secret' not in args[i + 1]: - args[i + 1].append(luks_default_key_secret_opt) - args.insert(i + 2, '--object') - args.insert(i + 3, luks_default_secret_object) - else: - args = ['-o', luks_default_key_secret_opt, - '--object', luks_default_secret_object] + args - - args.insert(0, 'create') - - return qemu_img(*args) + return qemu_img('create', *args) def qemu_img_measure(*args): return json.loads(qemu_img_pipe("measure", "--output", "json", *args)) -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The test prints qcow2 header fields which depends on chosen compression type. So, let's be explicit in what compression type we want and independent of IMGOPTS. Test both existing compression types. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-8-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/303 | 25 ++++++++++++++++--------- tests/qemu-iotests/303.out | 30 +++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 10 deletions(-) diff --git a/tests/qemu-iotests/303 b/tests/qemu-iotests/303 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/303 +++ b/tests/qemu-iotests/303 @@ -XXX,XX +XXX,XX @@ def add_bitmap(num, begin, end, disabled): log('') -qemu_img_create('-f', iotests.imgfmt, disk, '10M') - -add_bitmap(1, 0, 6, False) -add_bitmap(2, 6, 8, True) -dump = ['./qcow2.py', disk, 'dump-header'] -subprocess.run(dump) -# Dump the metadata in JSON format -dump.append('-j') -subprocess.run(dump) +def test(compression_type: str, json_output: bool) -> None: + qemu_img_create('-f', iotests.imgfmt, + '-o', f'compression_type={compression_type}', + disk, '10M') + add_bitmap(1, 0, 6, False) + add_bitmap(2, 6, 8, True) + + cmd = ['./qcow2.py', disk, 'dump-header'] + if json_output: + cmd.append('-j') + + subprocess.run(cmd) + + +test('zlib', False) +test('zstd', True) diff --git a/tests/qemu-iotests/303.out b/tests/qemu-iotests/303.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/303.out +++ b/tests/qemu-iotests/303.out @@ -XXX,XX +XXX,XX @@ extra_data_size 0 Bitmap table type size offset 0 all-zeroes 0 0 +Add bitmap 1 +wrote 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +wrote 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +wrote 1048576/1048576 bytes at offset 2097152 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +wrote 1048576/1048576 bytes at offset 3145728 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +wrote 1048576/1048576 bytes at offset 4194304 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +wrote 1048576/1048576 bytes at offset 5242880 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + + +Add bitmap 2 +wrote 1048576/1048576 bytes at offset 6291456 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +wrote 1048576/1048576 bytes at offset 7340032 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + + { "magic": 1363560955, "version": 3, @@ -XXX,XX +XXX,XX @@ Bitmap table type size offset "refcount_table_clusters": 1, "nb_snapshots": 0, "snapshot_offset": 0, - "incompatible_features": 0, + "incompatible_features": 8, "compatible_features": 0, "autoclear_features": 1, "refcount_order": 4, -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The test checks different options. It of course fails if set IMGOPTS='compression_type=zstd'. So, let's be explicit in what compression type we want and independent of IMGOPTS. Test both existing compression types. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-9-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/065 | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tests/qemu-iotests/065 b/tests/qemu-iotests/065 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/065 +++ b/tests/qemu-iotests/065 @@ -XXX,XX +XXX,XX @@ class TestQMP(TestImageInfoSpecific): class TestQCow2(TestQemuImgInfo): '''Testing a qcow2 version 2 image''' - img_options = 'compat=0.10' + img_options = 'compat=0.10,compression_type=zlib' json_compare = { 'compat': '0.10', 'refcount-bits': 16, 'compression-type': 'zlib' } human_compare = [ 'compat: 0.10', 'compression type: zlib', @@ -XXX,XX +XXX,XX @@ class TestQCow2(TestQemuImgInfo): class TestQCow3NotLazy(TestQemuImgInfo): '''Testing a qcow2 version 3 image with lazy refcounts disabled''' - img_options = 'compat=1.1,lazy_refcounts=off' + img_options = 'compat=1.1,lazy_refcounts=off,compression_type=zstd' json_compare = { 'compat': '1.1', 'lazy-refcounts': False, 'refcount-bits': 16, 'corrupt': False, - 'compression-type': 'zlib', 'extended-l2': False } - human_compare = [ 'compat: 1.1', 'compression type: zlib', + 'compression-type': 'zstd', 'extended-l2': False } + human_compare = [ 'compat: 1.1', 'compression type: zstd', 'lazy refcounts: false', 'refcount bits: 16', 'corrupt: false', 'extended l2: false' ] class TestQCow3Lazy(TestQemuImgInfo): '''Testing a qcow2 version 3 image with lazy refcounts enabled''' - img_options = 'compat=1.1,lazy_refcounts=on' + img_options = 'compat=1.1,lazy_refcounts=on,compression_type=zlib' json_compare = { 'compat': '1.1', 'lazy-refcounts': True, 'refcount-bits': 16, 'corrupt': False, 'compression-type': 'zlib', 'extended-l2': False } @@ -XXX,XX +XXX,XX @@ class TestQCow3Lazy(TestQemuImgInfo): class TestQCow3NotLazyQMP(TestQMP): '''Testing a qcow2 version 3 image with lazy refcounts disabled, opening with lazy refcounts enabled''' - img_options = 'compat=1.1,lazy_refcounts=off' + img_options = 'compat=1.1,lazy_refcounts=off,compression_type=zlib' qemu_options = 'lazy-refcounts=on' compare = { 'compat': '1.1', 'lazy-refcounts': False, 'refcount-bits': 16, 'corrupt': False, @@ -XXX,XX +XXX,XX @@ class TestQCow3NotLazyQMP(TestQMP): class TestQCow3LazyQMP(TestQMP): '''Testing a qcow2 version 3 image with lazy refcounts enabled, opening with lazy refcounts disabled''' - img_options = 'compat=1.1,lazy_refcounts=on' + img_options = 'compat=1.1,lazy_refcounts=on,compression_type=zstd' qemu_options = 'lazy-refcounts=off' compare = { 'compat': '1.1', 'lazy-refcounts': True, 'refcount-bits': 16, 'corrupt': False, - 'compression-type': 'zlib', 'extended-l2': False } + 'compression-type': 'zstd', 'extended-l2': False } TestImageInfoSpecific = None TestQemuImgInfo = None -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The only "feature" of this "Formatting ..." line is that we have to update it every time we add new option. Let's drop it. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-10-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/149.out | 21 --------------------- tests/qemu-iotests/237.out | 3 --- tests/qemu-iotests/255.out | 4 ---- tests/qemu-iotests/274.out | 29 ----------------------------- tests/qemu-iotests/280.out | 1 - tests/qemu-iotests/296.out | 10 +++------- tests/qemu-iotests/iotests.py | 10 ++++++++-- 7 files changed, 11 insertions(+), 67 deletions(-) diff --git a/tests/qemu-iotests/149.out b/tests/qemu-iotests/149.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/149.out +++ b/tests/qemu-iotests/149.out @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha1.img # ================= qemu-img aes-256-xts-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-aes-256-xts-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha1.img qiotest-145-aes-256-xts-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-twofish-256-xts-plain64-sha1.img # ================= qemu-img twofish-256-xts-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=twofish-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-twofish-256-xts-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-twofish-256-xts-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=twofish-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-twofish-256-xts-plain64-sha1.img qiotest-145-twofish-256-xts-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-serpent-256-xts-plain64-sha1.img # ================= qemu-img serpent-256-xts-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=serpent-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-serpent-256-xts-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-serpent-256-xts-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=serpent-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-serpent-256-xts-plain64-sha1.img qiotest-145-serpent-256-xts-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img # ================= qemu-img cast5-128-cbc-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=cast5-128,cipher-mode=cbc,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=cast5-128 cipher-mode=cbc ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img qiotest-145-cast5-128-cbc-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-cbc-plain-sha1.img # ================= qemu-img aes-256-cbc-plain-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=cbc,ivgen-alg=plain,hash-alg=sha1 TEST_DIR/luks-aes-256-cbc-plain-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-cbc-plain-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=cbc ivgen-alg=plain hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-plain-sha1.img qiotest-145-aes-256-cbc-plain-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-cbc-plain64-sha1.img # ================= qemu-img aes-256-cbc-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=cbc,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-aes-256-cbc-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-cbc-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=cbc ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-plain64-sha1.img qiotest-145-aes-256-cbc-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img # ================= qemu-img aes-256-cbc-essiv-sha256-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=cbc,ivgen-alg=essiv,hash-alg=sha1,ivgen-hash-alg=sha256 TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=cbc ivgen-alg=essiv ivgen-hash-alg=sha256 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img qiotest-145-aes-256-cbc-essiv-sha256-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img # ================= qemu-img aes-256-xts-essiv-sha256-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=essiv,hash-alg=sha1,ivgen-hash-alg=sha256 TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=essiv ivgen-hash-alg=sha256 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img qiotest-145-aes-256-xts-essiv-sha256-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img # ================= qemu-img aes-128-xts-plain64-sha256-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-128,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-128 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img qiotest-145-aes-128-xts-plain64-sha256-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img # ================= qemu-img aes-192-xts-plain64-sha256-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-192,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-192 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img qiotest-145-aes-192-xts-plain64-sha256-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-twofish-128-xts-plain64-sha1.img # ================= qemu-img twofish-128-xts-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=twofish-128,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-twofish-128-xts-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-twofish-128-xts-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=twofish-128 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-twofish-128-xts-plain64-sha1.img qiotest-145-twofish-128-xts-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-serpent-128-xts-plain64-sha1.img # ================= qemu-img serpent-128-xts-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=serpent-128,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-serpent-128-xts-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-serpent-128-xts-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=serpent-128 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-serpent-128-xts-plain64-sha1.img qiotest-145-serpent-128-xts-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-serpent-192-xts-plain64-sha1.img # ================= qemu-img serpent-192-xts-plain64-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=serpent-192,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha1 TEST_DIR/luks-serpent-192-xts-plain64-sha1.img 4194304M -Formatting 'TEST_DIR/luks-serpent-192-xts-plain64-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=serpent-192 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-serpent-192-xts-plain64-sha1.img qiotest-145-serpent-192-xts-plain64-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha224.img # ================= qemu-img aes-256-xts-plain64-sha224 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha224 TEST_DIR/luks-aes-256-xts-plain64-sha224.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain64-sha224.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha224 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha224.img qiotest-145-aes-256-xts-plain64-sha224 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha256.img # ================= qemu-img aes-256-xts-plain64-sha256 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha256 TEST_DIR/luks-aes-256-xts-plain64-sha256.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain64-sha256.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha256 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha256.img qiotest-145-aes-256-xts-plain64-sha256 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha384.img # ================= qemu-img aes-256-xts-plain64-sha384 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha384 TEST_DIR/luks-aes-256-xts-plain64-sha384.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain64-sha384.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha384 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha384.img qiotest-145-aes-256-xts-plain64-sha384 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha512.img # ================= qemu-img aes-256-xts-plain64-sha512 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=sha512 TEST_DIR/luks-aes-256-xts-plain64-sha512.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain64-sha512.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=sha512 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha512.img qiotest-145-aes-256-xts-plain64-sha512 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img # ================= qemu-img aes-256-xts-plain64-ripemd160 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain64,hash-alg=ripemd160 TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain64 hash-alg=ripemd160 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img qiotest-145-aes-256-xts-plain64-ripemd160 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img # ================= qemu-img aes-256-xts-plain-sha1-pwallslots ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=c2xvdDE=,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=xts,ivgen-alg=plain,hash-alg=sha1 TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=xts ivgen-alg=plain hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img qiotest-145-aes-256-xts-plain-sha1-pwallslots @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img # ================= qemu-img aes-256-cbc-essiv-auto-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=cbc,ivgen-alg=essiv,hash-alg=sha1 TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=cbc ivgen-alg=essiv hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img qiotest-145-aes-256-cbc-essiv-auto-sha1 @@ -XXX,XX +XXX,XX @@ unlink TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img # ================= qemu-img aes-256-cbc-plain64-sha256-sha1 ================= # Create image qemu-img create -f luks --object secret,id=sec0,data=MTIzNDU2,format=base64 -o key-secret=sec0,iter-time=10,cipher-alg=aes-256,cipher-mode=cbc,ivgen-alg=plain64,hash-alg=sha1,ivgen-hash-alg=sha256 TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img 4194304M -Formatting 'TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img', fmt=luks size=4398046511104 key-secret=sec0 cipher-alg=aes-256 cipher-mode=cbc ivgen-alg=plain64 ivgen-hash-alg=sha256 hash-alg=sha1 iter-time=10 # Open dev sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img qiotest-145-aes-256-cbc-plain64-sha256-sha1 diff --git a/tests/qemu-iotests/237.out b/tests/qemu-iotests/237.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/237.out +++ b/tests/qemu-iotests/237.out @@ -XXX,XX +XXX,XX @@ Job failed: Cannot find device='this doesn't exist' nor node-name='this doesn't === Other subformats === -Formatting 'TEST_DIR/PID-t.vmdk.1', fmt=vmdk size=0 compat6=off hwversion=undefined -Formatting 'TEST_DIR/PID-t.vmdk.2', fmt=vmdk size=0 compat6=off hwversion=undefined -Formatting 'TEST_DIR/PID-t.vmdk.3', fmt=vmdk size=0 compat6=off hwversion=undefined == Missing extent == diff --git a/tests/qemu-iotests/255.out b/tests/qemu-iotests/255.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/255.out +++ b/tests/qemu-iotests/255.out @@ -XXX,XX +XXX,XX @@ Finishing a commit job with background reads === Create backing chain and start VM === -Formatting 'TEST_DIR/PID-t.qcow2.mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16 === Start background read requests === @@ -XXX,XX +XXX,XX @@ Closing the VM while a job is being cancelled === Create images and start VM === -Formatting 'TEST_DIR/PID-src.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-dst.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 lazy_refcounts=off refcount_bits=16 wrote 1048576/1048576 bytes at offset 0 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ == Commit tests == -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing HMP commit (top -> mid) === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing QMP active commit (top -> mid) === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing qemu-img commit (top -> base) === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing QMP active commit (top -> base) === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 == Resize tests == === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=6442450944 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1073741824 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 5368709120 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 5368709120 { "start": 1073741824, "length": 7516192768, "depth": 0, "present": true, "zero": true, "data": false}] === preallocation=metadata === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=34359738368 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=32212254720 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 33285996544 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 33285996544 { "start": 34896609280, "length": 536870912, "depth": 0, "present": true, "zero": true, "data": false, "offset": 2685075456}] === preallocation=falloc === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=10485760 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=5242880 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 9437184 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 9437184 { "start": 5242880, "length": 10485760, "depth": 0, "present": true, "zero": false, "data": true, "offset": 327680}] === preallocation=full === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=16777216 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=8388608 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 11534336 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 11534336 { "start": 8388608, "length": 4194304, "depth": 0, "present": true, "zero": false, "data": true, "offset": 327680}] === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=393216 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=259072 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 259072 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 259072 { "start": 262144, "length": 262144, "depth": 0, "present": true, "zero": true, "data": false}] === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=409600 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=262144 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 344064 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 344064 { "start": 262144, "length": 262144, "depth": 0, "present": true, "zero": true, "data": false}] === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=524288 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=262144 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 wrote 65536/65536 bytes at offset 446464 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) diff --git a/tests/qemu-iotests/280.out b/tests/qemu-iotests/280.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/280.out +++ b/tests/qemu-iotests/280.out @@ -XXX,XX +XXX,XX @@ -Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16 === Launch VM === Enabling migration QMP events on VM... diff --git a/tests/qemu-iotests/296.out b/tests/qemu-iotests/296.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/296.out +++ b/tests/qemu-iotests/296.out @@ -XXX,XX +XXX,XX @@ -Formatting 'TEST_DIR/test.img', fmt=luks size=1048576 key-secret=keysec0 iter-time=10 {"execute": "job-dismiss", "arguments": {"id": "job0"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Job failed: Failed to get shared "consistent read" lock qemu-img: Failed to get shared "consistent read" lock Is another process using the image [TEST_DIR/test.img]? -.Formatting 'TEST_DIR/test.img', fmt=luks size=1048576 key-secret=keysec0 iter-time=10 - +. Job failed: Block node is read-only {"execute": "job-dismiss", "arguments": {"id": "job0"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Job failed: Failed to get shared "consistent read" lock {"return": {}} {"execute": "job-dismiss", "arguments": {"id": "job0"}} {"return": {}} -.Formatting 'TEST_DIR/test.img', fmt=luks size=1048576 key-secret=keysec0 iter-time=10 - +. {"return": {}} {"error": {"class": "GenericError", "desc": "Failed to get \"write\" lock"}} -.Formatting 'TEST_DIR/test.img', fmt=luks size=1048576 key-secret=keysec0 iter-time=10 - +. {"return": {}} {"return": {}} . diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def qemu_tool_popen(args: Sequence[str], def qemu_tool_pipe_and_status(tool: str, args: Sequence[str], - connect_stderr: bool = True) -> Tuple[str, int]: + connect_stderr: bool = True, + drop_successful_output: bool = False) \ + -> Tuple[str, int]: """ Run a tool and return both its output and its exit code """ @@ -XXX,XX +XXX,XX @@ def qemu_tool_pipe_and_status(tool: str, args: Sequence[str], cmd = ' '.join(args) sys.stderr.write(f'{tool} received signal \ {-subp.returncode}: {cmd}\n') + if drop_successful_output and subp.returncode == 0: + output = '' return (output, subp.returncode) def qemu_img_create_prepare_args(args: List[str]) -> List[str]: @@ -XXX,XX +XXX,XX @@ def qemu_img_pipe_and_status(*args: str) -> Tuple[str, int]: """ Run qemu-img and return both its output and its exit code """ + is_create = bool(args and args[0] == 'create') full_args = qemu_img_args + qemu_img_create_prepare_args(list(args)) - return qemu_tool_pipe_and_status('qemu-img', full_args) + return qemu_tool_pipe_and_status('qemu-img', full_args, + drop_successful_output=is_create) def qemu_img(*args: str) -> int: '''Run qemu-img and return the exit code''' -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We want iotests pass with both the default zlib compression and with IMGOPTS='compression_type=zstd'. Actually the only test that is interested in real compression type in test output is 287 (test for qcow2 compression type) and it's in bash. So for now we can safely filter out compression type in all qcow2 tests. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-11-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/206.out | 10 +++++----- tests/qemu-iotests/242.out | 10 +++++----- tests/qemu-iotests/274.out | 10 +++++----- tests/qemu-iotests/iotests.py | 2 ++ 4 files changed, 17 insertions(+), 15 deletions(-) diff --git a/tests/qemu-iotests/206.out b/tests/qemu-iotests/206.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/206.out +++ b/tests/qemu-iotests/206.out @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 32 MiB (33554432 bytes) cluster_size: 2097152 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 1 corrupt: false @@ -XXX,XX +XXX,XX @@ backing file: TEST_IMG.base backing file format: IMGFMT Format specific information: compat: 0.10 - compression type: zlib + compression type: COMPRESSION_TYPE refcount bits: 16 === Successful image creation (encrypted) === @@ -XXX,XX +XXX,XX @@ encrypted: yes cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 encrypt: diff --git a/tests/qemu-iotests/242.out b/tests/qemu-iotests/242.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/242.out +++ b/tests/qemu-iotests/242.out @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false bitmaps: [0]: @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false bitmaps: [0]: @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false bitmaps: [0]: @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false bitmaps: [0]: diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ backing file: TEST_DIR/PID-base backing file format: IMGFMT Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ backing file: TEST_DIR/PID-base backing file format: IMGFMT Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ backing file: TEST_DIR/PID-base backing file format: IMGFMT Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 2 MiB (2097152 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ backing file: TEST_DIR/PID-base backing file format: IMGFMT Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def filter_img_info(output, filename): 'uuid: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX', line) line = re.sub('cid: [0-9]+', 'cid: XXXXXXXXXX', line) + line = re.sub('(compression type: )(zlib|zstd)', r'\1COMPRESSION_TYPE', + line) lines.append(line) return '\n'.join(lines) -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Instead of qemu_img_log("info", ..) use generic helper img_info_log(). img_info_log() has smarter logic. For example it use filter_img_info() to filter output, which in turns filter a compression type. So it will help us in future when we implement a possibility to use zstd compression by default (with help of some runtime config file or maybe build option). For now to test you should recompile qemu with a small addition into block/qcow2.c before "if (qcow2_opts->has_compression_type": if (!qcow2_opts->has_compression_type && version >= 3) { qcow2_opts->has_compression_type = true; qcow2_opts->compression_type = QCOW2_COMPRESSION_TYPE_ZSTD; } Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-12-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/302 | 4 +++- tests/qemu-iotests/302.out | 7 +++---- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/tests/qemu-iotests/302 b/tests/qemu-iotests/302 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/302 +++ b/tests/qemu-iotests/302 @@ -XXX,XX +XXX,XX @@ from iotests import ( qemu_img_measure, qemu_io, qemu_nbd_popen, + img_info_log, ) iotests.script_initialize(supported_fmts=["qcow2"]) @@ -XXX,XX +XXX,XX @@ with tarfile.open(tar_file, "w") as tar: tar_file): iotests.log("=== Target image info ===") + # Not img_info_log as it enforces imgfmt, but now we print info on raw qemu_img_log("info", nbd_uri) qemu_img( @@ -XXX,XX +XXX,XX @@ with tarfile.open(tar_file, "w") as tar: nbd_uri) iotests.log("=== Converted image info ===") - qemu_img_log("info", nbd_uri) + img_info_log(nbd_uri) iotests.log("=== Converted image check ===") qemu_img_log("check", nbd_uri) diff --git a/tests/qemu-iotests/302.out b/tests/qemu-iotests/302.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/302.out +++ b/tests/qemu-iotests/302.out @@ -XXX,XX +XXX,XX @@ virtual size: 448 KiB (458752 bytes) disk size: unavailable === Converted image info === -image: nbd+unix:///exp?socket=SOCK_DIR/PID-nbd-sock -file format: qcow2 +image: TEST_IMG +file format: IMGFMT virtual size: 1 GiB (1073741824 bytes) -disk size: unavailable cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> If image doesn't have any compressed cluster we can easily switch to zlib compression, which may allow to downgrade the image. That's mostly needed to support IMGOPTS='compression_type=zstd' in some iotests which do qcow2 downgrade. While being here also fix checkpatch complain against '#' in printf formatting. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-13-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/qcow2.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 56 insertions(+), 2 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, return bs->drv->bdrv_co_preadv_part(bs, offset, qiov->size, qiov, 0, 0); } +static int qcow2_has_compressed_clusters(BlockDriverState *bs) +{ + int64_t offset = 0; + int64_t bytes = bdrv_getlength(bs); + + if (bytes < 0) { + return bytes; + } + + while (bytes != 0) { + int ret; + QCow2SubclusterType type; + unsigned int cur_bytes = MIN(INT_MAX, bytes); + uint64_t host_offset; + + ret = qcow2_get_host_offset(bs, offset, &cur_bytes, &host_offset, + &type); + if (ret < 0) { + return ret; + } + + if (type == QCOW2_SUBCLUSTER_COMPRESSED) { + return 1; + } + + offset += cur_bytes; + bytes -= cur_bytes; + } + + return 0; +} + /* * Downgrades an image's version. To achieve this, any incompatible features * have to be removed. @@ -XXX,XX +XXX,XX @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, * the first place; if that happens nonetheless, returning -ENOTSUP is the * best thing to do anyway */ - if (s->incompatible_features) { + if (s->incompatible_features & ~QCOW2_INCOMPAT_COMPRESSION) { error_setg(errp, "Cannot downgrade an image with incompatible features " - "%#" PRIx64 " set", s->incompatible_features); + "0x%" PRIx64 " set", + s->incompatible_features & ~QCOW2_INCOMPAT_COMPRESSION); return -ENOTSUP; } @@ -XXX,XX +XXX,XX @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, return ret; } + if (s->incompatible_features & QCOW2_INCOMPAT_COMPRESSION) { + ret = qcow2_has_compressed_clusters(bs); + if (ret < 0) { + error_setg(errp, "Failed to check block status"); + return -EINVAL; + } + if (ret) { + error_setg(errp, "Cannot downgrade an image with zstd compression " + "type and existing compressed clusters"); + return -ENOTSUP; + } + /* + * No compressed clusters for now, so just chose default zlib + * compression. + */ + s->incompatible_features &= ~QCOW2_INCOMPAT_COMPRESSION; + s->compression_type = QCOW2_COMPRESSION_TYPE_ZLIB; + } + + assert(s->incompatible_features == 0); + s->qcow_version = target_version; ret = qcow2_update_header(bs); if (ret < 0) { -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We'll use it in tests instead of explicit qcow2.py. Then we are going to add some filtering in _qcow2_dump_header. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-14-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/common.rc | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _require_one_device_of() _notrun "$* not available" } +_qcow2_dump_header() +{ + img="$1" + if [ -z "$img" ]; then + img="$TEST_IMG" + fi + + $PYTHON qcow2.py "$img" dump-header +} + # make sure this script returns success true -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to add filtering in _qcow2_dump_header and want all tests use it. The patch is generated by commands: cd tests/qemu-iotests sed -ie 's/$PYTHON qcow2.py "$TEST_IMG" dump-header\($\| \)/_qcow2_dump_header\1/' ??? tests/* (the difficulty is to avoid converting dump-header-exts) Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-15-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/031 | 6 +++--- tests/qemu-iotests/036 | 6 +++--- tests/qemu-iotests/039 | 20 ++++++++++---------- tests/qemu-iotests/060 | 20 ++++++++++---------- tests/qemu-iotests/061 | 36 ++++++++++++++++++------------------ tests/qemu-iotests/137 | 2 +- tests/qemu-iotests/287 | 8 ++++---- 7 files changed, 49 insertions(+), 49 deletions(-) diff --git a/tests/qemu-iotests/031 b/tests/qemu-iotests/031 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/031 +++ b/tests/qemu-iotests/031 @@ -XXX,XX +XXX,XX @@ for compat in "compat=0.10" "compat=1.1"; do echo _make_test_img -o $compat 64M $PYTHON qcow2.py "$TEST_IMG" add-header-ext 0x12345678 "This is a test header extension" - $PYTHON qcow2.py "$TEST_IMG" dump-header + _qcow2_dump_header _check_test_img echo echo === Rewrite header with no backing file === echo $QEMU_IMG rebase -u -b "" "$TEST_IMG" - $PYTHON qcow2.py "$TEST_IMG" dump-header + _qcow2_dump_header _check_test_img echo echo === Add a backing file and format === echo $QEMU_IMG rebase -u -b "/some/backing/file/path" -F host_device "$TEST_IMG" - $PYTHON qcow2.py "$TEST_IMG" dump-header + _qcow2_dump_header done # success, all done diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/036 +++ b/tests/qemu-iotests/036 @@ -XXX,XX +XXX,XX @@ $PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 63 # Without feature table $PYTHON qcow2.py "$TEST_IMG" del-header-ext 0x6803f857 -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features +_qcow2_dump_header | grep features $PYTHON qcow2.py "$TEST_IMG" dump-header-exts _img_info @@ -XXX,XX +XXX,XX @@ echo === Create image with unknown autoclear feature bit === echo _make_test_img 64M $PYTHON qcow2.py "$TEST_IMG" set-feature-bit autoclear 63 -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features +_qcow2_dump_header | grep features $PYTHON qcow2.py "$TEST_IMG" dump-header-exts echo @@ -XXX,XX +XXX,XX @@ echo === Repair image === echo _check_test_img -r all -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features +_qcow2_dump_header | grep features $PYTHON qcow2.py "$TEST_IMG" dump-header-exts # success, all done diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/039 +++ b/tests/qemu-iotests/039 @@ -XXX,XX +XXX,XX @@ _make_test_img -o "compat=1.1,lazy_refcounts=on" $size $QEMU_IO -c "write -P 0x5a 0 512" "$TEST_IMG" | _filter_qemu_io # The dirty bit must not be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features _check_test_img echo @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write -P 0x5a 0 512" \ | _filter_qemu_io # The dirty bit must be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features _check_test_img echo @@ -XXX,XX +XXX,XX @@ echo "== Read-only access must still work ==" $QEMU_IO -r -c "read -P 0x5a 0 512" "$TEST_IMG" | _filter_qemu_io # The dirty bit must be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features echo echo "== Repairing the image file must succeed ==" @@ -XXX,XX +XXX,XX @@ echo "== Repairing the image file must succeed ==" _check_test_img -r all # The dirty bit must not be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features echo echo "== Data should still be accessible after repair ==" @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write -P 0x5a 0 512" \ | _filter_qemu_io # The dirty bit must be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features $QEMU_IO -c "write 0 512" "$TEST_IMG" | _filter_qemu_io # The dirty bit must not be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features echo echo "== Creating an image file with lazy_refcounts=off ==" @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write -P 0x5a 0 512" \ | _filter_qemu_io # The dirty bit must not be set since lazy_refcounts=off -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features _check_test_img echo @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write 0 512" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG commit "$TEST_IMG" # The dirty bit must not be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features $PYTHON qcow2.py "$TEST_IMG".base dump-header | grep incompatible_features _check_test_img @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "reopen -o lazy-refcounts=on" \ | _filter_qemu_io # The dirty bit must be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features _check_test_img _make_test_img -o "compat=1.1,lazy_refcounts=on" $size @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "reopen -o lazy-refcounts=off" \ | _filter_qemu_io # The dirty bit must not be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features _check_test_img diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ poke_file "$TEST_IMG" "$l1_offset" "\x80\x00\x00\x00\x00\x03\x00\x00" _check_test_img # The corrupt bit should not be set anyway -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features # Try to write something, thereby forcing the corrupt bit to be set $QEMU_IO -c "$OPEN_RW" -c "write -P 0x2a 0 512" | _filter_qemu_io # The corrupt bit must now be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features # This information should be available through qemu-img info _img_info --format-specific @@ -XXX,XX +XXX,XX @@ poke_file "$TEST_IMG" "$(($rb_offset+8))" "\x00\x01" # Redirect new data cluster onto refcount block poke_file "$TEST_IMG" "$l2_offset" "\x80\x00\x00\x00\x00\x02\x00\x00" _check_test_img -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features $QEMU_IO -c "$OPEN_RW" -c "write -P 0x2a 0 512" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features # Try to fix it _check_test_img -r all # The corrupt bit should be cleared -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features # Look if it's really really fixed $QEMU_IO -c "$OPEN_RW" -c "write -P 0x2a 0 512" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features echo echo "=== Testing cluster data reference into inactive L2 table ===" @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "$OPEN_RW" -c "write -P 2 0 512" | _filter_qemu_io poke_file "$TEST_IMG" "$l2_offset_after_snapshot" \ "\x80\x00\x00\x00\x00\x04\x00\x00" _check_test_img -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features $QEMU_IO -c "$OPEN_RW" -c "write -P 3 0 512" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features _check_test_img -r all -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features $QEMU_IO -c "$OPEN_RW" -c "write -P 4 0 512" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features # Check data $QEMU_IO -c "$OPEN_RO" -c "read -P 4 0 512" | _filter_qemu_io diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ echo "=== Testing version downgrade with zero expansion ===" echo _make_test_img -o "compat=1.1,lazy_refcounts=on" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io _check_test_img @@ -XXX,XX +XXX,XX @@ _make_test_img -o "compat=1.1,lazy_refcounts=on" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c "write -z 32M 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c map "$TEST_IMG" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IMG amend -o "compat=0.10" --image-opts \ driver=qcow2,file.filename=$TEST_IMG,l2-cache-entry-size=4096 -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c "read -P 0 32M 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c map "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ _make_test_img -o "compat=1.1,lazy_refcounts=on" 64M _NO_VALGRIND \ $QEMU_IO -c "write -P 0x2a 0 128k" -c flush \ -c "sigraise $(kill -l KILL)" "$TEST_IMG" 2>&1 | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IO -c "read -P 0x2a 0 128k" "$TEST_IMG" | _filter_qemu_io _check_test_img @@ -XXX,XX +XXX,XX @@ echo _make_test_img -o "compat=1.1" 64M $PYTHON qcow2.py "$TEST_IMG" set-feature-bit compatible 42 $PYTHON qcow2.py "$TEST_IMG" set-feature-bit autoclear 42 -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header _check_test_img echo @@ -XXX,XX +XXX,XX @@ echo "=== Testing version upgrade and resize ===" echo _make_test_img -o "compat=0.10" 64M $QEMU_IO -c "write -P 0x2a 42M 64k" "$TEST_IMG" | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IMG amend -o "compat=1.1,lazy_refcounts=on,size=128M" "$TEST_IMG" -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IO -c "read -P 0x2a 42M 64k" "$TEST_IMG" | _filter_qemu_io _check_test_img @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write -P 0x2a 24M 64k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG snapshot -c foo "$TEST_IMG" $QEMU_IMG resize "$TEST_IMG" 64M && echo "unexpected pass" -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep '^\(version\|size\|nb_snap\)' +_qcow2_dump_header | grep '^\(version\|size\|nb_snap\)' $QEMU_IMG amend -o "compat=1.1,size=128M" "$TEST_IMG" || echo "unexpected fail" -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep '^\(version\|size\|nb_snap\)' +_qcow2_dump_header | grep '^\(version\|size\|nb_snap\)' $QEMU_IMG snapshot -c bar "$TEST_IMG" $QEMU_IMG resize --shrink "$TEST_IMG" 64M || echo "unexpected fail" -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep '^\(version\|size\|nb_snap\)' +_qcow2_dump_header | grep '^\(version\|size\|nb_snap\)' $QEMU_IMG amend -o "compat=0.10,size=32M" "$TEST_IMG" && echo "unexpected pass" -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep '^\(version\|size\|nb_snap\)' +_qcow2_dump_header | grep '^\(version\|size\|nb_snap\)' $QEMU_IMG snapshot -a bar "$TEST_IMG" || echo "unexpected fail" -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep '^\(version\|size\|nb_snap\)' +_qcow2_dump_header | grep '^\(version\|size\|nb_snap\)' $QEMU_IMG snapshot -d bar "$TEST_IMG" $QEMU_IMG amend -o "compat=0.10,size=32M" "$TEST_IMG" || echo "unexpected fail" -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep '^\(version\|size\|nb_snap\)' +_qcow2_dump_header | grep '^\(version\|size\|nb_snap\)' _check_test_img @@ -XXX,XX +XXX,XX @@ _make_test_img -o "compat=1.1,lazy_refcounts=on" 64M _NO_VALGRIND \ $QEMU_IO -c "write -P 0x2a 0 128k" -c flush \ -c "sigraise $(kill -l KILL)" "$TEST_IMG" 2>&1 | _filter_qemu_io -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IMG amend -o "lazy_refcounts=off" "$TEST_IMG" -$PYTHON qcow2.py "$TEST_IMG" dump-header +_qcow2_dump_header $QEMU_IO -c "read -P 0x2a 0 128k" "$TEST_IMG" | _filter_qemu_io _check_test_img diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/137 +++ b/tests/qemu-iotests/137 @@ -XXX,XX +XXX,XX @@ $QEMU_IO \ # The dirty bit must not be set # (Filter the external data file bit) -if $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features \ +if _qcow2_dump_header | grep incompatible_features \ | grep -q '\<0\>' then echo 'ERROR: Dirty bit set' diff --git a/tests/qemu-iotests/287 b/tests/qemu-iotests/287 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/287 +++ b/tests/qemu-iotests/287 @@ -XXX,XX +XXX,XX @@ echo echo "=== Testing compression type incompatible bit setting for zlib ===" echo _make_test_img -o compression_type=zlib 64M -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features echo echo "=== Testing compression type incompatible bit setting for zstd ===" echo _make_test_img -o compression_type=zstd 64M -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features echo echo "=== Testing zlib with incompatible bit set ===" @@ -XXX,XX +XXX,XX @@ echo _make_test_img -o compression_type=zlib 64M $PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 3 # to make sure the bit was actually set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features if $QEMU_IMG info "$TEST_IMG" >/dev/null 2>&1 ; then echo "Error: The image opened successfully. The image must not be opened." @@ -XXX,XX +XXX,XX @@ echo _make_test_img -o compression_type=zstd 64M $PYTHON qcow2.py "$TEST_IMG" set-header incompatible_features 0 # to make sure the bit was actually unset -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +_qcow2_dump_header | grep incompatible_features if $QEMU_IMG info "$TEST_IMG" >/dev/null 2>&1 ; then echo "Error: The image opened successfully. The image must not be opened." -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> _qcow2_dump_header has filter for compression type, so this change makes test pass with IMGOPTS='compression_type=zstd'. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-16-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/039 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/039 +++ b/tests/qemu-iotests/039 @@ -XXX,XX +XXX,XX @@ $QEMU_IMG commit "$TEST_IMG" # The dirty bit must not be set _qcow2_dump_header | grep incompatible_features -$PYTHON qcow2.py "$TEST_IMG".base dump-header | grep incompatible_features +_qcow2_dump_header "$TEST_IMG".base | grep incompatible_features _check_test_img TEST_IMG="$TEST_IMG".base _check_test_img -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We want iotests pass with both the default zlib compression and with IMGOPTS='compression_type=zstd'. Actually the only test that is interested in real compression type in test output is 287 (test for qcow2 compression type), so implement specific option for it. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-17-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/060.out | 2 +- tests/qemu-iotests/061.out | 12 ++++++------ tests/qemu-iotests/082.out | 14 +++++++------- tests/qemu-iotests/198.out | 4 ++-- tests/qemu-iotests/287 | 8 ++++---- tests/qemu-iotests/common.filter | 8 ++++++++ tests/qemu-iotests/common.rc | 14 +++++++++++++- 7 files changed, 41 insertions(+), 21 deletions(-) diff --git a/tests/qemu-iotests/060.out b/tests/qemu-iotests/060.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/060.out +++ b/tests/qemu-iotests/060.out @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: true diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/061.out +++ b/tests/qemu-iotests/061.out @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 data file: foo @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 data file raw: false @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data diff --git a/tests/qemu-iotests/082.out b/tests/qemu-iotests/082.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/082.out +++ b/tests/qemu-iotests/082.out @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 4096 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 8192 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 4096 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 8192 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 130 MiB (136314880 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 132 MiB (138412032 bytes) cluster_size: 65536 Format specific information: compat: 1.1 - compression type: zlib + compression type: COMPRESSION_TYPE lazy refcounts: true refcount bits: 16 corrupt: false diff --git a/tests/qemu-iotests/198.out b/tests/qemu-iotests/198.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/198.out +++ b/tests/qemu-iotests/198.out @@ -XXX,XX +XXX,XX @@ image: json:{ /* filtered */ } file format: IMGFMT virtual size: 16 MiB (16777216 bytes) Format specific information: - compression type: zlib + compression type: COMPRESSION_TYPE encrypt: ivgen alg: plain64 hash alg: sha256 @@ -XXX,XX +XXX,XX @@ virtual size: 16 MiB (16777216 bytes) backing file: TEST_DIR/t.IMGFMT.base backing file format: IMGFMT Format specific information: - compression type: zlib + compression type: COMPRESSION_TYPE encrypt: ivgen alg: plain64 hash alg: sha256 diff --git a/tests/qemu-iotests/287 b/tests/qemu-iotests/287 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/287 +++ b/tests/qemu-iotests/287 @@ -XXX,XX +XXX,XX @@ echo echo "=== Testing compression type incompatible bit setting for zlib ===" echo _make_test_img -o compression_type=zlib 64M -_qcow2_dump_header | grep incompatible_features +_qcow2_dump_header --no-filter-compression | grep incompatible_features echo echo "=== Testing compression type incompatible bit setting for zstd ===" echo _make_test_img -o compression_type=zstd 64M -_qcow2_dump_header | grep incompatible_features +_qcow2_dump_header --no-filter-compression | grep incompatible_features echo echo "=== Testing zlib with incompatible bit set ===" @@ -XXX,XX +XXX,XX @@ echo _make_test_img -o compression_type=zlib 64M $PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 3 # to make sure the bit was actually set -_qcow2_dump_header | grep incompatible_features +_qcow2_dump_header --no-filter-compression | grep incompatible_features if $QEMU_IMG info "$TEST_IMG" >/dev/null 2>&1 ; then echo "Error: The image opened successfully. The image must not be opened." @@ -XXX,XX +XXX,XX @@ echo _make_test_img -o compression_type=zstd 64M $PYTHON qcow2.py "$TEST_IMG" set-header incompatible_features 0 # to make sure the bit was actually unset -_qcow2_dump_header | grep incompatible_features +_qcow2_dump_header --no-filter-compression | grep incompatible_features if $QEMU_IMG info "$TEST_IMG" >/dev/null 2>&1 ; then echo "Error: The image opened successfully. The image must not be opened." diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_img_info() -e "/block_state_zero: \\(on\\|off\\)/d" \ -e "/log_size: [0-9]\\+/d" \ -e "s/iters: [0-9]\\+/iters: 1024/" \ + -e 's/\(compression type: \)\(zlib\|zstd\)/\1COMPRESSION_TYPE/' \ -e "s/uuid: [-a-f0-9]\\+/uuid: 00000000-0000-0000-0000-000000000000/" | \ while IFS='' read -r line; do if [[ $format_specific == 1 ]]; then @@ -XXX,XX +XXX,XX @@ _filter_authz_check_tls() $SED -e 's/TLS x509 authz check for .* is denied/TLS x509 authz check for DISTINGUISHED-NAME is denied/' } +_filter_qcow2_compression_type_bit() +{ + $SED -e 's/\(incompatible_features\s\+\)\[3\(, \)\?/\1[/' \ + -e 's/\(incompatible_features.*\), 3\]/\1]/' \ + -e 's/\(incompatible_features.*\), 3\(,.*\)/\1\2/' +} + # make sure this script returns success true diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _img_info() -e "s#$TEST_DIR#TEST_DIR#g" \ -e "s#$SOCK_DIR/fuse-#TEST_DIR/#g" \ -e "s#$IMGFMT#IMGFMT#g" \ + -e 's/\(compression type: \)\(zlib\|zstd\)/\1COMPRESSION_TYPE/' \ -e "/^disk size:/ D" \ -e "/actual-size/ D" | \ while IFS='' read -r line; do @@ -XXX,XX +XXX,XX @@ _require_one_device_of() _qcow2_dump_header() { + if [[ "$1" == "--no-filter-compression" ]]; then + local filter_compression=0 + shift + else + local filter_compression=1 + fi + img="$1" if [ -z "$img" ]; then img="$TEST_IMG" fi - $PYTHON qcow2.py "$img" dump-header + if [[ $filter_compression == 0 ]]; then + $PYTHON qcow2.py "$img" dump-header + else + $PYTHON qcow2.py "$img" dump-header | _filter_qcow2_compression_type_bit + fi } # make sure this script returns success -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Don't touch other incompatible bits, like compression-type. This makes the test pass with IMGOPTS='compression_type=zstd'. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-18-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/060 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ _make_test_img 64M # Let the refblock appear unaligned poke_file "$TEST_IMG" "$rt_offset" "\x00\x00\x00\x00\xff\xff\x2a\x00" # Mark the image dirty, thus forcing an automatic check when opening it -poke_file "$TEST_IMG" 72 "\x00\x00\x00\x00\x00\x00\x00\x01" +$PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 0 # Open the image (qemu should refuse to do so) $QEMU_IO -c close "$TEST_IMG" 2>&1 | _filter_testdir | _filter_imgfmt -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The test-case "Corrupted size field in compressed cluster descriptor" heavily depends on zlib compression type. So, make it explicit. This way test passes with IMGOPTS='compression_type=zstd'. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20211223160144.1097696-19-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/214 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/214 +++ b/tests/qemu-iotests/214 @@ -XXX,XX +XXX,XX @@ echo # The L2 entries of the two compressed clusters are located at # 0x800000 and 0x800008, their original values are 0x4008000000a00000 # and 0x4008000000a00802 (5 sectors for compressed data each). -_make_test_img 8M -o cluster_size=2M +_make_test_img 8M -o cluster_size=2M,compression_type=zlib $QEMU_IO -c "write -c -P 0x11 0 2M" -c "write -c -P 0x11 2M 2M" "$TEST_IMG" \ 2>&1 | _filter_qemu_io | _filter_testdir -- 2.34.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> compression_type can't be used if we want to create image with compat=0.10. So, skip these tests, not many of them. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211223160144.1097696-20-vsementsov@virtuozzo.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/031 | 5 +++-- tests/qemu-iotests/051 | 5 +++-- tests/qemu-iotests/061 | 6 +++++- tests/qemu-iotests/112 | 3 ++- tests/qemu-iotests/290 | 2 +- 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/tests/qemu-iotests/031 b/tests/qemu-iotests/031 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/031 +++ b/tests/qemu-iotests/031 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file fuse # We want to test compat=0.10, which does not support external data -# files or refcount widths other than 16 -_unsupported_imgopts data_file 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# files or refcount widths other than 16 or compression type +_unsupported_imgopts data_file compression_type \ + 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' CLUSTER_SIZE=65536 diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/051 +++ b/tests/qemu-iotests/051 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2 _supported_proto file # A compat=0.10 image is created in this test which does not support anything # other than refcount_bits=16; -# it also will not support an external data file -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file +# it also will not support an external data file and compression type +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file \ + compression_type _require_drivers nbd if [ "$QEMU_DEFAULT_MACHINE" = "pc" ]; then diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ _supported_os Linux # not work with it; # we have explicit tests for various cluster sizes, the remaining tests # require the default 64k cluster -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file cluster_size +# we don't have explicit tests for zstd qcow2 compression type, as zstd may be +# not compiled in. And we can't create compat images with comression type +# extension +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file \ + cluster_size compression_type echo echo "=== Testing version downgrade with zero expansion ===" diff --git a/tests/qemu-iotests/112 b/tests/qemu-iotests/112 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/112 +++ b/tests/qemu-iotests/112 @@ -XXX,XX +XXX,XX @@ _supported_proto file fuse # This test will set refcount_bits on its own which would conflict with the # manual setting; compat will be overridden as well; # and external data files do not work well with our refcount testing -_unsupported_imgopts refcount_bits 'compat=0.10' data_file +# also, compression type is not supported with compat=0.10 used in test +_unsupported_imgopts refcount_bits 'compat=0.10' data_file compression_type print_refcount_bits() { diff --git a/tests/qemu-iotests/290 b/tests/qemu-iotests/290 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/290 +++ b/tests/qemu-iotests/290 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file fuse _supported_os Linux -_unsupported_imgopts 'compat=0.10' refcount_bits data_file +_unsupported_imgopts 'compat=0.10' refcount_bits data_file compression_type echo echo "### Test 'qemu-io -c discard' on a QCOW2 image without a backing file" -- 2.34.1 After migration, the permissions the guest device wants to impose on its BlockBackend are stored in blk->perm and blk->shared_perm. In blk_root_activate(), we take our permissions, but keep all shared permissions open by calling `blk_set_perm(blk->perm, BLK_PERM_ALL)`. Only afterwards (immediately or later, depending on the runstate) do we restrict the shared permissions by calling `blk_set_perm(blk->perm, blk->shared_perm)`. Unfortunately, our first call with shared_perm=BLK_PERM_ALL has overwritten blk->shared_perm to be BLK_PERM_ALL, so this is a no-op and the set of shared permissions is not restricted. Fix this bug by saving the set of shared permissions before invoking blk_set_perm() with BLK_PERM_ALL and restoring it afterwards. Fixes: 5f7772c4d0cf32f4e779fcd5a69ae4dae24aeebf ("block-backend: Defer shared_perm tightening migration completion") Reported-by: Peng Liang <liangpeng10@huawei.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20211125135317.186576-2-hreitz@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Peng Liang <liangpeng10@huawei.com> --- block/block-backend.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static void blk_root_activate(BdrvChild *child, Error **errp) { BlockBackend *blk = child->opaque; Error *local_err = NULL; + uint64_t saved_shared_perm; if (!blk->disable_perm) { return; @@ -XXX,XX +XXX,XX @@ static void blk_root_activate(BdrvChild *child, Error **errp) blk->disable_perm = false; + /* + * blk->shared_perm contains the permissions we want to share once + * migration is really completely done. For now, we need to share + * all; but we also need to retain blk->shared_perm, which is + * overwritten by a successful blk_set_perm() call. Save it and + * restore it below. + */ + saved_shared_perm = blk->shared_perm; + blk_set_perm(blk, blk->perm, BLK_PERM_ALL, &local_err); if (local_err) { error_propagate(errp, local_err); blk->disable_perm = true; return; } + blk->shared_perm = saved_shared_perm; if (runstate_check(RUN_STATE_INMIGRATE)) { /* Activation can happen when migration process is still active, for -- 2.34.1 This test checks that a raw image in use by a virtio-blk device does not share the WRITE permission both before and after migration. Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- .../qemu-iotests/tests/migration-permissions | 101 ++++++++++++++++++ .../tests/migration-permissions.out | 5 + 2 files changed, 106 insertions(+) create mode 100755 tests/qemu-iotests/tests/migration-permissions create mode 100644 tests/qemu-iotests/tests/migration-permissions.out diff --git a/tests/qemu-iotests/tests/migration-permissions b/tests/qemu-iotests/tests/migration-permissions new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/tests/migration-permissions @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# group: migration +# +# Copyright (C) 2021 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +import os +import iotests +from iotests import imgfmt, qemu_img_create, qemu_io + + +test_img = os.path.join(iotests.test_dir, 'test.img') +mig_sock = os.path.join(iotests.sock_dir, 'mig.sock') + + +class TestMigrationPermissions(iotests.QMPTestCase): + def setUp(self): + qemu_img_create('-f', imgfmt, test_img, '1M') + + # Set up two VMs (source and destination) accessing the same raw + # image file with a virtio-blk device; prepare the destination for + # migration with .add_incoming() and enable migration events + vms = [None, None] + for i in range(2): + vms[i] = iotests.VM(path_suffix=f'{i}') + vms[i].add_blockdev(f'file,node-name=prot,filename={test_img}') + vms[i].add_blockdev(f'{imgfmt},node-name=fmt,file=prot') + vms[i].add_device('virtio-blk,drive=fmt') + + if i == 1: + vms[i].add_incoming(f'unix:{mig_sock}') + + vms[i].launch() + + result = vms[i].qmp('migrate-set-capabilities', + capabilities=[ + {'capability': 'events', 'state': True} + ]) + self.assert_qmp(result, 'return', {}) + + self.vm_s = vms[0] + self.vm_d = vms[1] + + def tearDown(self): + self.vm_s.shutdown() + self.vm_d.shutdown() + try: + os.remove(mig_sock) + except FileNotFoundError: + pass + os.remove(test_img) + + # Migrate an image in use by a virtio-blk device to another VM and + # verify that the WRITE permission is unshared both before and after + # migration + def test_post_migration_permissions(self): + # Try to access the image R/W, which should fail because virtio-blk + # has not been configured with share-rw=on + log = qemu_io('-f', imgfmt, '-c', 'quit', test_img) + if not log.strip(): + print('ERROR (pre-migration): qemu-io should not be able to ' + 'access this image, but it reported no error') + else: + # This is the expected output + assert 'Is another process using the image' in log + + # Now migrate the VM + self.vm_s.qmp('migrate', uri=f'unix:{mig_sock}') + assert self.vm_s.wait_migration(None) + assert self.vm_d.wait_migration(None) + + # Try the same qemu-io access again, verifying that the WRITE + # permission remains unshared + log = qemu_io('-f', imgfmt, '-c', 'quit', test_img) + if not log.strip(): + print('ERROR (post-migration): qemu-io should not be able to ' + 'access this image, but it reported no error') + else: + # This is the expected output + assert 'Is another process using the image' in log + + +if __name__ == '__main__': + # Only works with raw images because we are testing the + # BlockBackend permissions; image format drivers may additionally + # unshare permissions and thus tamper with the result + iotests.main(supported_fmts=['raw'], + supported_protocols=['file']) diff --git a/tests/qemu-iotests/tests/migration-permissions.out b/tests/qemu-iotests/tests/migration-permissions.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/tests/migration-permissions.out @@ -XXX,XX +XXX,XX @@ +. +---------------------------------------------------------------------- +Ran 1 tests + +OK -- 2.34.1 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> The comment "disk I/O throttling" doesn't make any sense at all any more. It was added in commit 0563e191516 to describe bdrv_io_limits_enable()/disable(), which were removed in commit 97148076, so the comment is just a forgotten leftover. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20220131125615.74612-1-eesposit@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/block/block.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ typedef unsigned int BdrvChildRole; char *bdrv_perm_names(uint64_t perm); uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm); -/* disk I/O throttling */ void bdrv_init(void); void bdrv_init_with_whitelist(void); bool bdrv_uses_whitelist(void); -- 2.34.1 The following changes since commit ac793156f650ae2d77834932d72224175ee69086: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20201020-1' into staging (2020-10-20 21:11:35 +0100) are available in the Git repository at: https://gitlab.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to 32a3fd65e7e3551337fd26bfc0e2f899d70c028c: iotests: add commit top->base cases to 274 (2020-10-22 09:55:39 +0100) ---------------------------------------------------------------- Pull request v2: * Fix format string issues on 32-bit hosts [Peter] * Fix qemu-nbd.c CONFIG_POSIX ifdef issue [Eric] * Fix missing eventfd.h header on macOS [Peter] * Drop unreliable vhost-user-blk test (will send a new patch when ready) [Peter] This pull request contains the vhost-user-blk server by Coiby Xu along with my additions, block/nvme.c alignment and hardware error statistics by Philippe Mathieu-Daudé, and bdrv_co_block_status_above() fixes by Vladimir Sementsov-Ogievskiy. ---------------------------------------------------------------- Coiby Xu (6): libvhost-user: Allow vu_message_read to be replaced libvhost-user: remove watch for kick_fd when de-initialize vu-dev util/vhost-user-server: generic vhost user server block: move logical block size check function to a common utility function block/export: vhost-user block device backend server MAINTAINERS: Add vhost-user block device backend server maintainer Philippe Mathieu-Daudé (1): block/nvme: Add driver statistics for access alignment and hw errors Stefan Hajnoczi (16): util/vhost-user-server: s/fileds/fields/ typo fix util/vhost-user-server: drop unnecessary QOM cast util/vhost-user-server: drop unnecessary watch deletion block/export: consolidate request structs into VuBlockReq util/vhost-user-server: drop unused DevicePanicNotifier util/vhost-user-server: fix memory leak in vu_message_read() util/vhost-user-server: check EOF when reading payload util/vhost-user-server: rework vu_client_trip() coroutine lifecycle block/export: report flush errors block/export: convert vhost-user-blk server to block export API util/vhost-user-server: move header to include/ util/vhost-user-server: use static library in meson.build qemu-storage-daemon: avoid compiling blockdev_ss twice block: move block exports to libblockdev block/export: add iothread and fixed-iothread options block/export: add vhost-user-blk multi-queue support Vladimir Sementsov-Ogievskiy (5): block/io: fix bdrv_co_block_status_above block/io: bdrv_common_block_status_above: support include_base block/io: bdrv_common_block_status_above: support bs == base block/io: fix bdrv_is_allocated_above iotests: add commit top->base cases to 274 MAINTAINERS | 9 + qapi/block-core.json | 24 +- qapi/block-export.json | 36 +- block/coroutines.h | 2 + block/export/vhost-user-blk-server.h | 19 + contrib/libvhost-user/libvhost-user.h | 21 + include/qemu/vhost-user-server.h | 65 +++ util/block-helpers.h | 19 + block/export/export.c | 37 +- block/export/vhost-user-blk-server.c | 431 ++++++++++++++++++++ block/io.c | 132 +++--- block/nvme.c | 27 ++ block/qcow2.c | 16 +- contrib/libvhost-user/libvhost-user-glib.c | 2 +- contrib/libvhost-user/libvhost-user.c | 15 +- hw/core/qdev-properties-system.c | 31 +- nbd/server.c | 2 - qemu-nbd.c | 21 +- softmmu/vl.c | 4 + stubs/blk-exp-close-all.c | 7 + tests/vhost-user-bridge.c | 2 + tools/virtiofsd/fuse_virtio.c | 4 +- util/block-helpers.c | 46 +++ util/vhost-user-server.c | 446 +++++++++++++++++++++ block/export/meson.build | 3 +- contrib/libvhost-user/meson.build | 1 + meson.build | 22 +- nbd/meson.build | 2 + storage-daemon/meson.build | 3 +- stubs/meson.build | 1 + tests/qemu-iotests/274 | 20 + tests/qemu-iotests/274.out | 68 ++++ util/meson.build | 4 + 33 files changed, 1420 insertions(+), 122 deletions(-) create mode 100644 block/export/vhost-user-blk-server.h create mode 100644 include/qemu/vhost-user-server.h create mode 100644 util/block-helpers.h create mode 100644 block/export/vhost-user-blk-server.c create mode 100644 stubs/blk-exp-close-all.c create mode 100644 util/block-helpers.c create mode 100644 util/vhost-user-server.c -- 2.26.2 From: Philippe Mathieu-Daudé <philmd@redhat.com> Keep statistics of some hardware errors, and number of aligned/unaligned I/O accesses. QMP example booting a full RHEL 8.3 aarch64 guest: { "execute": "query-blockstats" } { "return": [ { "device": "", "node-name": "drive0", "stats": { "flush_total_time_ns": 6026948, "wr_highest_offset": 3383991230464, "wr_total_time_ns": 807450995, "failed_wr_operations": 0, "failed_rd_operations": 0, "wr_merged": 3, "wr_bytes": 50133504, "failed_unmap_operations": 0, "failed_flush_operations": 0, "account_invalid": false, "rd_total_time_ns": 1846979900, "flush_operations": 130, "wr_operations": 659, "rd_merged": 1192, "rd_bytes": 218244096, "account_failed": false, "idle_time_ns": 2678641497, "rd_operations": 7406, }, "driver-specific": { "driver": "nvme", "completion-errors": 0, "unaligned-accesses": 2959, "aligned-accesses": 4477 }, "qdev": "/machine/peripheral-anon/device[0]/virtio-backend" } ] } Suggested-by: Stefan Hajnoczi <stefanha@gmail.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20201001162939.1567915-1-philmd@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-core.json | 24 +++++++++++++++++++++++- block/nvme.c | 27 +++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 1 deletion(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ 'discard-nb-failed': 'uint64', 'discard-bytes-ok': 'uint64' } } +## +# @BlockStatsSpecificNvme: +# +# NVMe driver statistics +# +# @completion-errors: The number of completion errors. +# +# @aligned-accesses: The number of aligned accesses performed by +# the driver. +# +# @unaligned-accesses: The number of unaligned accesses performed by +# the driver. +# +# Since: 5.2 +## +{ 'struct': 'BlockStatsSpecificNvme', + 'data': { + 'completion-errors': 'uint64', + 'aligned-accesses': 'uint64', + 'unaligned-accesses': 'uint64' } } + ## # @BlockStatsSpecific: # @@ -XXX,XX +XXX,XX @@ 'discriminator': 'driver', 'data': { 'file': 'BlockStatsSpecificFile', - 'host_device': 'BlockStatsSpecificFile' } } + 'host_device': 'BlockStatsSpecificFile', + 'nvme': 'BlockStatsSpecificNvme' } } ## # @BlockStats: diff --git a/block/nvme.c b/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -XXX,XX +XXX,XX @@ struct BDRVNVMeState { /* PCI address (required for nvme_refresh_filename()) */ char *device; + + struct { + uint64_t completion_errors; + uint64_t aligned_accesses; + uint64_t unaligned_accesses; + } stats; }; #define NVME_BLOCK_OPT_DEVICE "device" @@ -XXX,XX +XXX,XX @@ static bool nvme_process_completion(NVMeQueuePair *q) break; } ret = nvme_translate_error(c); + if (ret) { + s->stats.completion_errors++; + } q->cq.head = (q->cq.head + 1) % NVME_QUEUE_SIZE; if (!q->cq.head) { q->cq_phase = !q->cq_phase; @@ -XXX,XX +XXX,XX @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, assert(QEMU_IS_ALIGNED(bytes, s->page_size)); assert(bytes <= s->max_transfer); if (nvme_qiov_aligned(bs, qiov)) { + s->stats.aligned_accesses++; return nvme_co_prw_aligned(bs, offset, bytes, qiov, is_write, flags); } + s->stats.unaligned_accesses++; trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write); buf = qemu_try_memalign(s->page_size, bytes); @@ -XXX,XX +XXX,XX @@ static void nvme_unregister_buf(BlockDriverState *bs, void *host) qemu_vfio_dma_unmap(s->vfio, host); } +static BlockStatsSpecific *nvme_get_specific_stats(BlockDriverState *bs) +{ + BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1); + BDRVNVMeState *s = bs->opaque; + + stats->driver = BLOCKDEV_DRIVER_NVME; + stats->u.nvme = (BlockStatsSpecificNvme) { + .completion_errors = s->stats.completion_errors, + .aligned_accesses = s->stats.aligned_accesses, + .unaligned_accesses = s->stats.unaligned_accesses, + }; + + return stats; +} + static const char *const nvme_strong_runtime_opts[] = { NVME_BLOCK_OPT_DEVICE, NVME_BLOCK_OPT_NAMESPACE, @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = { .bdrv_refresh_filename = nvme_refresh_filename, .bdrv_refresh_limits = nvme_refresh_limits, .strong_runtime_opts = nvme_strong_runtime_opts, + .bdrv_get_specific_stats = nvme_get_specific_stats, .bdrv_detach_aio_context = nvme_detach_aio_context, .bdrv_attach_aio_context = nvme_attach_aio_context, -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Allow vu_message_read to be replaced by one which will make use of the QIOChannel functions. Thus reading vhost-user message won't stall the guest. For slave channel, we still use the default vu_message_read. Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200918080912.321299-2-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++ contrib/libvhost-user/libvhost-user-glib.c | 2 +- contrib/libvhost-user/libvhost-user.c | 14 +++++++------- tests/vhost-user-bridge.c | 2 ++ tools/virtiofsd/fuse_virtio.c | 4 ++-- 5 files changed, 33 insertions(+), 10 deletions(-) diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.h +++ b/contrib/libvhost-user/libvhost-user.h @@ -XXX,XX +XXX,XX @@ */ #define VHOST_USER_MAX_RAM_SLOTS 32 +#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) + typedef enum VhostSetConfigType { VHOST_SET_CONFIG_TYPE_MASTER = 0, VHOST_SET_CONFIG_TYPE_MIGRATION = 1, @@ -XXX,XX +XXX,XX @@ typedef uint64_t (*vu_get_features_cb) (VuDev *dev); typedef void (*vu_set_features_cb) (VuDev *dev, uint64_t features); typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg, int *do_reply); +typedef bool (*vu_read_msg_cb) (VuDev *dev, int sock, VhostUserMsg *vmsg); typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started); typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx); typedef int (*vu_get_config_cb) (VuDev *dev, uint8_t *config, uint32_t len); @@ -XXX,XX +XXX,XX @@ struct VuDev { bool broken; uint16_t max_queues; + /* @read_msg: custom method to read vhost-user message + * + * Read data from vhost_user socket fd and fill up + * the passed VhostUserMsg *vmsg struct. + * + * If reading fails, it should close the received set of file + * descriptors as socket message's auxiliary data. + * + * For the details, please refer to vu_message_read in libvhost-user.c + * which will be used by default if not custom method is provided when + * calling vu_init + * + * Returns: true if vhost-user message successfully received, + * otherwise return false. + * + */ + vu_read_msg_cb read_msg; /* @set_watch: add or update the given fd to the watch set, * call cb when condition is met */ vu_set_watch_cb set_watch; @@ -XXX,XX +XXX,XX @@ bool vu_init(VuDev *dev, uint16_t max_queues, int socket, vu_panic_cb panic, + vu_read_msg_cb read_msg, vu_set_watch_cb set_watch, vu_remove_watch_cb remove_watch, const VuDevIface *iface); diff --git a/contrib/libvhost-user/libvhost-user-glib.c b/contrib/libvhost-user/libvhost-user-glib.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user-glib.c +++ b/contrib/libvhost-user/libvhost-user-glib.c @@ -XXX,XX +XXX,XX @@ vug_init(VugDev *dev, uint16_t max_queues, int socket, g_assert(dev); g_assert(iface); - if (!vu_init(&dev->parent, max_queues, socket, panic, set_watch, + if (!vu_init(&dev->parent, max_queues, socket, panic, NULL, set_watch, remove_watch, iface)) { return false; } diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -XXX,XX +XXX,XX @@ /* The version of inflight buffer */ #define INFLIGHT_VERSION 1 -#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) - /* The version of the protocol we support */ #define VHOST_USER_VERSION 1 #define LIBVHOST_USER_DEBUG 0 @@ -XXX,XX +XXX,XX @@ have_userfault(void) } static bool -vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) +vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) { char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; struct iovec iov = { @@ -XXX,XX +XXX,XX @@ vu_process_message_reply(VuDev *dev, const VhostUserMsg *vmsg) goto out; } - if (!vu_message_read(dev, dev->slave_fd, &msg_reply)) { + if (!vu_message_read_default(dev, dev->slave_fd, &msg_reply)) { goto out; } @@ -XXX,XX +XXX,XX @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) /* Wait for QEMU to confirm that it's registered the handler for the * faults. */ - if (!vu_message_read(dev, dev->sock, vmsg) || + if (!dev->read_msg(dev, dev->sock, vmsg) || vmsg->size != sizeof(vmsg->payload.u64) || vmsg->payload.u64 != 0) { vu_panic(dev, "failed to receive valid ack for postcopy set-mem-table"); @@ -XXX,XX +XXX,XX @@ vu_dispatch(VuDev *dev) int reply_requested; bool need_reply, success = false; - if (!vu_message_read(dev, dev->sock, &vmsg)) { + if (!dev->read_msg(dev, dev->sock, &vmsg)) { goto end; } @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, uint16_t max_queues, int socket, vu_panic_cb panic, + vu_read_msg_cb read_msg, vu_set_watch_cb set_watch, vu_remove_watch_cb remove_watch, const VuDevIface *iface) @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, dev->sock = socket; dev->panic = panic; + dev->read_msg = read_msg ? read_msg : vu_message_read_default; dev->set_watch = set_watch; dev->remove_watch = remove_watch; dev->iface = iface; @@ -XXX,XX +XXX,XX @@ static void _vu_queue_notify(VuDev *dev, VuVirtq *vq, bool sync) vu_message_write(dev, dev->slave_fd, &vmsg); if (ack) { - vu_message_read(dev, dev->slave_fd, &vmsg); + vu_message_read_default(dev, dev->slave_fd, &vmsg); } return; } diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c index XXXXXXX..XXXXXXX 100644 --- a/tests/vhost-user-bridge.c +++ b/tests/vhost-user-bridge.c @@ -XXX,XX +XXX,XX @@ vubr_accept_cb(int sock, void *ctx) VHOST_USER_BRIDGE_MAX_QUEUES, conn_fd, vubr_panic, + NULL, vubr_set_watch, vubr_remove_watch, &vuiface)) { @@ -XXX,XX +XXX,XX @@ vubr_new(const char *path, bool client) VHOST_USER_BRIDGE_MAX_QUEUES, dev->sock, vubr_panic, + NULL, vubr_set_watch, vubr_remove_watch, &vuiface)) { diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c index XXXXXXX..XXXXXXX 100644 --- a/tools/virtiofsd/fuse_virtio.c +++ b/tools/virtiofsd/fuse_virtio.c @@ -XXX,XX +XXX,XX @@ int virtio_session_mount(struct fuse_session *se) se->vu_socketfd = data_sock; se->virtio_dev->se = se; pthread_rwlock_init(&se->virtio_dev->vu_dispatch_rwlock, NULL); - vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, fv_set_watch, - fv_remove_watch, &fv_iface); + vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL, + fv_set_watch, fv_remove_watch, &fv_iface); return 0; } -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> When the client is running in gdb and quit command is run in gdb, QEMU will still dispatch the event which will cause segment fault in the callback function. Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-3-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- contrib/libvhost-user/libvhost-user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -XXX,XX +XXX,XX @@ vu_deinit(VuDev *dev) } if (vq->kick_fd != -1) { + dev->remove_watch(dev, vq->kick_fd); close(vq->kick_fd); vq->kick_fd = -1; } -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Sharing QEMU devices via vhost-user protocol. Only one vhost-user client can connect to the server one time. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-4-coiby.xu@gmail.com [Fixed size_t %lu -> %zu format string compiler error. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 65 ++++++ util/vhost-user-server.c | 428 +++++++++++++++++++++++++++++++++++++++ util/meson.build | 1 + 3 files changed, 494 insertions(+) create mode 100644 util/vhost-user-server.h create mode 100644 util/vhost-user-server.c diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU devices via vhost-user protocol + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ + +#ifndef VHOST_USER_SERVER_H +#define VHOST_USER_SERVER_H + +#include "contrib/libvhost-user/libvhost-user.h" +#include "io/channel-socket.h" +#include "io/channel-file.h" +#include "io/net-listener.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "standard-headers/linux/virtio_blk.h" + +typedef struct VuFdWatch { + VuDev *vu_dev; + int fd; /*kick fd*/ + void *pvt; + vu_watch_cb cb; + bool processing; + QTAILQ_ENTRY(VuFdWatch) next; +} VuFdWatch; + +typedef struct VuServer VuServer; +typedef void DevicePanicNotifierFn(VuServer *server); + +struct VuServer { + QIONetListener *listener; + AioContext *ctx; + DevicePanicNotifierFn *device_panic_notifier; + int max_queues; + const VuDevIface *vu_iface; + VuDev vu_dev; + QIOChannel *ioc; /* The I/O channel with the client */ + QIOChannelSocket *sioc; /* The underlying data channel with the client */ + /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ + QIOChannel *ioc_slave; + QIOChannelSocket *sioc_slave; + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ + QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; + /* restart coroutine co_trip if AIOContext is changed */ + bool aio_context_changed; + bool processing_msg; +}; + +bool vhost_user_server_start(VuServer *server, + SocketAddress *unix_socket, + AioContext *ctx, + uint16_t max_queues, + DevicePanicNotifierFn *device_panic_notifier, + const VuDevIface *vu_iface, + Error **errp); + +void vhost_user_server_stop(VuServer *server); + +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); + +#endif /* VHOST_USER_SERVER_H */ diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU devices via vhost-user protocol + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "qemu/main-loop.h" +#include "vhost-user-server.h" + +static void vmsg_close_fds(VhostUserMsg *vmsg) +{ + int i; + for (i = 0; i < vmsg->fd_num; i++) { + close(vmsg->fds[i]); + } +} + +static void vmsg_unblock_fds(VhostUserMsg *vmsg) +{ + int i; + for (i = 0; i < vmsg->fd_num; i++) { + qemu_set_nonblock(vmsg->fds[i]); + } +} + +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, + gpointer opaque); + +static void close_client(VuServer *server) +{ + /* + * Before closing the client + * + * 1. Let vu_client_trip stop processing new vhost-user msg + * + * 2. remove kick_handler + * + * 3. wait for the kick handler to be finished + * + * 4. wait for the current vhost-user msg to be finished processing + */ + + QIOChannelSocket *sioc = server->sioc; + /* When this is set vu_client_trip will stop new processing vhost-user message */ + server->sioc = NULL; + + VuFdWatch *vu_fd_watch, *next; + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, + NULL, NULL, NULL); + } + + while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (!vu_fd_watch->processing) { + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); + g_free(vu_fd_watch); + } + } + } + + while (server->processing_msg) { + if (server->ioc->read_coroutine) { + server->ioc->read_coroutine = NULL; + qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, + NULL, server->ioc); + server->processing_msg = false; + } + } + + vu_deinit(&server->vu_dev); + object_unref(OBJECT(sioc)); + object_unref(OBJECT(server->ioc)); +} + +static void panic_cb(VuDev *vu_dev, const char *buf) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + + /* avoid while loop in close_client */ + server->processing_msg = false; + + if (buf) { + error_report("vu_panic: %s", buf); + } + + if (server->sioc) { + close_client(server); + } + + if (server->device_panic_notifier) { + server->device_panic_notifier(server); + } + + /* + * Set the callback function for network listener so another + * vhost-user client can connect to this server + */ + qio_net_listener_set_client_func(server->listener, + vu_accept, + server, + NULL); +} + +static bool coroutine_fn +vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) +{ + struct iovec iov = { + .iov_base = (char *)vmsg, + .iov_len = VHOST_USER_HDR_SIZE, + }; + int rc, read_bytes = 0; + Error *local_err = NULL; + /* + * Store fds/nfds returned from qio_channel_readv_full into + * temporary variables. + * + * VhostUserMsg is a packed structure, gcc will complain about passing + * pointer to a packed structure member if we pass &VhostUserMsg.fd_num + * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, + * thus two temporary variables nfds and fds are used here. + */ + size_t nfds = 0, nfds_t = 0; + const size_t max_fds = G_N_ELEMENTS(vmsg->fds); + int *fds_t = NULL; + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + QIOChannel *ioc = server->ioc; + + if (!ioc) { + error_report_err(local_err); + goto fail; + } + + assert(qemu_in_coroutine()); + do { + /* + * qio_channel_readv_full may have short reads, keeping calling it + * until getting VHOST_USER_HDR_SIZE or 0 bytes in total + */ + rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); + if (rc < 0) { + if (rc == QIO_CHANNEL_ERR_BLOCK) { + qio_channel_yield(ioc, G_IO_IN); + continue; + } else { + error_report_err(local_err); + return false; + } + } + read_bytes += rc; + if (nfds_t > 0) { + if (nfds + nfds_t > max_fds) { + error_report("A maximum of %zu fds are allowed, " + "however got %zu fds now", + max_fds, nfds + nfds_t); + goto fail; + } + memcpy(vmsg->fds + nfds, fds_t, + nfds_t *sizeof(vmsg->fds[0])); + nfds += nfds_t; + g_free(fds_t); + } + if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { + break; + } + iov.iov_base = (char *)vmsg + read_bytes; + iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; + } while (true); + + vmsg->fd_num = nfds; + /* qio_channel_readv_full will make socket fds blocking, unblock them */ + vmsg_unblock_fds(vmsg); + if (vmsg->size > sizeof(vmsg->payload)) { + error_report("Error: too big message request: %d, " + "size: vmsg->size: %u, " + "while sizeof(vmsg->payload) = %zu", + vmsg->request, vmsg->size, sizeof(vmsg->payload)); + goto fail; + } + + struct iovec iov_payload = { + .iov_base = (char *)&vmsg->payload, + .iov_len = vmsg->size, + }; + if (vmsg->size) { + rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); + if (rc == -1) { + error_report_err(local_err); + goto fail; + } + } + + return true; + +fail: + vmsg_close_fds(vmsg); + + return false; +} + + +static void vu_client_start(VuServer *server); +static coroutine_fn void vu_client_trip(void *opaque) +{ + VuServer *server = opaque; + + while (!server->aio_context_changed && server->sioc) { + server->processing_msg = true; + vu_dispatch(&server->vu_dev); + server->processing_msg = false; + } + + if (server->aio_context_changed && server->sioc) { + server->aio_context_changed = false; + vu_client_start(server); + } +} + +static void vu_client_start(VuServer *server) +{ + server->co_trip = qemu_coroutine_create(vu_client_trip, server); + aio_co_enter(server->ctx, server->co_trip); +} + +/* + * a wrapper for vu_kick_cb + * + * since aio_dispatch can only pass one user data pointer to the + * callback function, pack VuDev and pvt into a struct. Then unpack it + * and pass them to vu_kick_cb + */ +static void kick_handler(void *opaque) +{ + VuFdWatch *vu_fd_watch = opaque; + vu_fd_watch->processing = true; + vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); + vu_fd_watch->processing = false; +} + + +static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) +{ + + VuFdWatch *vu_fd_watch, *next; + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (vu_fd_watch->fd == fd) { + return vu_fd_watch; + } + } + return NULL; +} + +static void +set_watch(VuDev *vu_dev, int fd, int vu_evt, + vu_watch_cb cb, void *pvt) +{ + + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + g_assert(vu_dev); + g_assert(fd >= 0); + g_assert(cb); + + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); + + if (!vu_fd_watch) { + VuFdWatch *vu_fd_watch = g_new0(VuFdWatch, 1); + + QTAILQ_INSERT_TAIL(&server->vu_fd_watches, vu_fd_watch, next); + + vu_fd_watch->fd = fd; + vu_fd_watch->cb = cb; + qemu_set_nonblock(fd); + aio_set_fd_handler(server->ioc->ctx, fd, true, kick_handler, + NULL, NULL, vu_fd_watch); + vu_fd_watch->vu_dev = vu_dev; + vu_fd_watch->pvt = pvt; + } +} + + +static void remove_watch(VuDev *vu_dev, int fd) +{ + VuServer *server; + g_assert(vu_dev); + g_assert(fd >= 0); + + server = container_of(vu_dev, VuServer, vu_dev); + + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); + + if (!vu_fd_watch) { + return; + } + aio_set_fd_handler(server->ioc->ctx, fd, true, NULL, NULL, NULL, NULL); + + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); + g_free(vu_fd_watch); +} + + +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, + gpointer opaque) +{ + VuServer *server = opaque; + + if (server->sioc) { + warn_report("Only one vhost-user client is allowed to " + "connect the server one time"); + return; + } + + if (!vu_init(&server->vu_dev, server->max_queues, sioc->fd, panic_cb, + vu_message_read, set_watch, remove_watch, server->vu_iface)) { + error_report("Failed to initialize libvhost-user"); + return; + } + + /* + * Unset the callback function for network listener to make another + * vhost-user client keeping waiting until this client disconnects + */ + qio_net_listener_set_client_func(server->listener, + NULL, + NULL, + NULL); + server->sioc = sioc; + /* + * Increase the object reference, so sioc will not freed by + * qio_net_listener_channel_func which will call object_unref(OBJECT(sioc)) + */ + object_ref(OBJECT(server->sioc)); + qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); + server->ioc = QIO_CHANNEL(sioc); + object_ref(OBJECT(server->ioc)); + qio_channel_attach_aio_context(server->ioc, server->ctx); + qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); + vu_client_start(server); +} + + +void vhost_user_server_stop(VuServer *server) +{ + if (server->sioc) { + close_client(server); + } + + if (server->listener) { + qio_net_listener_disconnect(server->listener); + object_unref(OBJECT(server->listener)); + } + +} + +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) +{ + VuFdWatch *vu_fd_watch, *next; + void *opaque = NULL; + IOHandler *io_read = NULL; + bool attach; + + server->ctx = ctx ? ctx : qemu_get_aio_context(); + + if (!server->sioc) { + /* not yet serving any client*/ + return; + } + + if (ctx) { + qio_channel_attach_aio_context(server->ioc, ctx); + server->aio_context_changed = true; + io_read = kick_handler; + attach = true; + } else { + qio_channel_detach_aio_context(server->ioc); + /* server->ioc->ctx keeps the old AioConext */ + ctx = server->ioc->ctx; + attach = false; + } + + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (vu_fd_watch->cb) { + opaque = attach ? vu_fd_watch : NULL; + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, + io_read, NULL, NULL, + opaque); + } + } +} + + +bool vhost_user_server_start(VuServer *server, + SocketAddress *socket_addr, + AioContext *ctx, + uint16_t max_queues, + DevicePanicNotifierFn *device_panic_notifier, + const VuDevIface *vu_iface, + Error **errp) +{ + QIONetListener *listener = qio_net_listener_new(); + if (qio_net_listener_open_sync(listener, socket_addr, 1, + errp) < 0) { + object_unref(OBJECT(listener)); + return false; + } + + /* zero out unspecified fileds */ + *server = (VuServer) { + .listener = listener, + .vu_iface = vu_iface, + .max_queues = max_queues, + .ctx = ctx, + .device_panic_notifier = device_panic_notifier, + }; + + qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); + + qio_net_listener_set_client_func(server->listener, + vu_accept, + server, + NULL); + + QTAILQ_INIT(&server->vu_fd_watches); + return true; +} diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('main-loop.c')) util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) + util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) util_ss.add(files('thread-pool.c', 'qemu-timer.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Move the constants from hw/core/qdev-properties.c to util/block-helpers.h so that knowledge of the min/max values is Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Acked-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20200918080912.321299-5-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/block-helpers.h | 19 +++++++++++++ hw/core/qdev-properties-system.c | 31 ++++----------------- util/block-helpers.c | 46 ++++++++++++++++++++++++++++++++ util/meson.build | 1 + 4 files changed, 71 insertions(+), 26 deletions(-) create mode 100644 util/block-helpers.h create mode 100644 util/block-helpers.c diff --git a/util/block-helpers.h b/util/block-helpers.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/block-helpers.h @@ -XXX,XX +XXX,XX @@ +#ifndef BLOCK_HELPERS_H +#define BLOCK_HELPERS_H + +#include "qemu/units.h" + +/* lower limit is sector size */ +#define MIN_BLOCK_SIZE INT64_C(512) +#define MIN_BLOCK_SIZE_STR "512 B" +/* + * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and + * matches qcow2 cluster size limit + */ +#define MAX_BLOCK_SIZE (2 * MiB) +#define MAX_BLOCK_SIZE_STR "2 MiB" + +void check_block_size(const char *id, const char *name, int64_t value, + Error **errp); + +#endif /* BLOCK_HELPERS_H */ diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/blockdev.h" #include "net/net.h" #include "hw/pci/pci.h" +#include "util/block-helpers.h" static bool check_prop_still_unset(DeviceState *dev, const char *name, const void *old_val, const char *new_val, @@ -XXX,XX +XXX,XX @@ const PropertyInfo qdev_prop_losttickpolicy = { /* --- blocksize --- */ -/* lower limit is sector size */ -#define MIN_BLOCK_SIZE 512 -#define MIN_BLOCK_SIZE_STR "512 B" -/* - * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and - * matches qcow2 cluster size limit - */ -#define MAX_BLOCK_SIZE (2 * MiB) -#define MAX_BLOCK_SIZE_STR "2 MiB" - static void set_blocksize(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, Property *prop = opaque; uint32_t *ptr = qdev_get_prop_ptr(dev, prop); uint64_t value; + Error *local_err = NULL; if (dev->realized) { qdev_prop_set_after_realize(dev, name, errp); @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, if (!visit_type_size(v, name, &value, errp)) { return; } - /* value of 0 means "unset" */ - if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { - error_setg(errp, - "Property %s.%s doesn't take value %" PRIu64 - " (minimum: " MIN_BLOCK_SIZE_STR - ", maximum: " MAX_BLOCK_SIZE_STR ")", - dev->id ? : "", name, value); + check_block_size(dev->id ? : "", name, value, &local_err); + if (local_err) { + error_propagate(errp, local_err); return; } - - /* We rely on power-of-2 blocksizes for bitmasks */ - if ((value & (value - 1)) != 0) { - error_setg(errp, - "Property %s.%s doesn't take value '%" PRId64 "', " - "it's not a power of 2", dev->id ?: "", name, (int64_t)value); - return; - } - *ptr = value; } diff --git a/util/block-helpers.c b/util/block-helpers.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/block-helpers.c @@ -XXX,XX +XXX,XX @@ +/* + * Block utility functions + * + * Copyright IBM, Corp. 2011 + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qapi/qmp/qerror.h" +#include "block-helpers.h" + +/** + * check_block_size: + * @id: The unique ID of the object + * @name: The name of the property being validated + * @value: The block size in bytes + * @errp: A pointer to an area to store an error + * + * This function checks that the block size meets the following conditions: + * 1. At least MIN_BLOCK_SIZE + * 2. No larger than MAX_BLOCK_SIZE + * 3. A power of 2 + */ +void check_block_size(const char *id, const char *name, int64_t value, + Error **errp) +{ + /* value of 0 means "unset" */ + if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { + error_setg(errp, QERR_PROPERTY_VALUE_OUT_OF_RANGE, + id, name, value, MIN_BLOCK_SIZE, MAX_BLOCK_SIZE); + return; + } + + /* We rely on power-of-2 blocksizes for bitmasks */ + if ((value & (value - 1)) != 0) { + error_setg(errp, + "Property %s.%s doesn't take value '%" PRId64 + "', it's not a power of 2", + id, name, value); + return; + } +} diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) + util_ss.add(files('block-helpers.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) util_ss.add(files('thread-pool.c', 'qemu-timer.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> By making use of libvhost-user, block device drive can be shared to the connected vhost-user client. Only one client can connect to the server one time. Since vhost-user-server needs a block drive to be created first, delay the creation of this object. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-6-coiby.xu@gmail.com [Shorten "vhost_user_blk_server" string to "vhost_user_blk" to avoid the following compiler warning: ../block/export/vhost-user-blk-server.c:178:50: error: ‘%s’ directive output truncated writing 21 bytes into a region of size 20 [-Werror=format-truncation=] and fix "Invalid size %ld ..." ssize_t format string arguments for 32-bit hosts. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.h | 36 ++ block/export/vhost-user-blk-server.c | 661 +++++++++++++++++++++++++++ softmmu/vl.c | 4 + block/meson.build | 1 + 4 files changed, 702 insertions(+) create mode 100644 block/export/vhost-user-blk-server.h create mode 100644 block/export/vhost-user-blk-server.c diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vhost-user-blk-server.h @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU block devices via vhost-user protocal + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ + +#ifndef VHOST_USER_BLK_SERVER_H +#define VHOST_USER_BLK_SERVER_H +#include "util/vhost-user-server.h" + +typedef struct VuBlockDev VuBlockDev; +#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" +#define VHOST_USER_BLK_SERVER(obj) \ + OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) + +/* vhost user block device */ +struct VuBlockDev { + Object parent_obj; + char *node_name; + SocketAddress *addr; + AioContext *ctx; + VuServer vu_server; + bool running; + uint32_t blk_size; + BlockBackend *backend; + QIOChannelSocket *sioc; + QTAILQ_ENTRY(VuBlockDev) next; + struct virtio_blk_config blkcfg; + bool writable; +}; + +#endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU block devices via vhost-user protocal + * + * Parts of the code based on nbd/server.c. + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "block/block.h" +#include "vhost-user-blk-server.h" +#include "qapi/error.h" +#include "qom/object_interfaces.h" +#include "sysemu/block-backend.h" +#include "util/block-helpers.h" + +enum { + VHOST_USER_BLK_MAX_QUEUES = 1, +}; +struct virtio_blk_inhdr { + unsigned char status; +}; + +typedef struct VuBlockReq { + VuVirtqElement *elem; + int64_t sector_num; + size_t size; + struct virtio_blk_inhdr *in; + struct virtio_blk_outhdr out; + VuServer *server; + struct VuVirtq *vq; +} VuBlockReq; + +static void vu_block_req_complete(VuBlockReq *req) +{ + VuDev *vu_dev = &req->server->vu_dev; + + /* IO size with 1 extra status byte */ + vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); + vu_queue_notify(vu_dev, req->vq); + + if (req->elem) { + free(req->elem); + } + + g_free(req); +} + +static VuBlockDev *get_vu_block_device_by_server(VuServer *server) +{ + return container_of(server, VuBlockDev, vu_server); +} + +static int coroutine_fn +vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, + uint32_t iovcnt, uint32_t type) +{ + struct virtio_blk_discard_write_zeroes desc; + ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); + if (unlikely(size != sizeof(desc))) { + error_report("Invalid size %zd, expect %zu", size, sizeof(desc)); + return -EINVAL; + } + + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); + uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, + le32_to_cpu(desc.num_sectors) << 9 }; + if (type == VIRTIO_BLK_T_DISCARD) { + if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + return 0; + } + } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { + if (blk_co_pwrite_zeroes(vdev_blk->backend, + range[0], range[1], 0) == 0) { + return 0; + } + } + + return -EINVAL; +} + +static void coroutine_fn vu_block_flush(VuBlockReq *req) +{ + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); + BlockBackend *backend = vdev_blk->backend; + blk_co_flush(backend); +} + +struct req_data { + VuServer *server; + VuVirtq *vq; + VuVirtqElement *elem; +}; + +static void coroutine_fn vu_block_virtio_process_req(void *opaque) +{ + struct req_data *data = opaque; + VuServer *server = data->server; + VuVirtq *vq = data->vq; + VuVirtqElement *elem = data->elem; + uint32_t type; + VuBlockReq *req; + + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + BlockBackend *backend = vdev_blk->backend; + + struct iovec *in_iov = elem->in_sg; + struct iovec *out_iov = elem->out_sg; + unsigned in_num = elem->in_num; + unsigned out_num = elem->out_num; + /* refer to hw/block/virtio_blk.c */ + if (elem->out_num < 1 || elem->in_num < 1) { + error_report("virtio-blk request missing headers"); + free(elem); + return; + } + + req = g_new0(VuBlockReq, 1); + req->server = server; + req->vq = vq; + req->elem = elem; + + if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, + sizeof(req->out)) != sizeof(req->out))) { + error_report("virtio-blk request outhdr too short"); + goto err; + } + + iov_discard_front(&out_iov, &out_num, sizeof(req->out)); + + if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) { + error_report("virtio-blk request inhdr too short"); + goto err; + } + + /* We always touch the last byte, so just see how big in_iov is. */ + req->in = (void *)in_iov[in_num - 1].iov_base + + in_iov[in_num - 1].iov_len + - sizeof(struct virtio_blk_inhdr); + iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr)); + + type = le32_to_cpu(req->out.type); + switch (type & ~VIRTIO_BLK_T_BARRIER) { + case VIRTIO_BLK_T_IN: + case VIRTIO_BLK_T_OUT: { + ssize_t ret = 0; + bool is_write = type & VIRTIO_BLK_T_OUT; + req->sector_num = le64_to_cpu(req->out.sector); + + int64_t offset = req->sector_num * vdev_blk->blk_size; + QEMUIOVector qiov; + if (is_write) { + qemu_iovec_init_external(&qiov, out_iov, out_num); + ret = blk_co_pwritev(backend, offset, qiov.size, + &qiov, 0); + } else { + qemu_iovec_init_external(&qiov, in_iov, in_num); + ret = blk_co_preadv(backend, offset, qiov.size, + &qiov, 0); + } + if (ret >= 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } + break; + } + case VIRTIO_BLK_T_FLUSH: + vu_block_flush(req); + req->in->status = VIRTIO_BLK_S_OK; + break; + case VIRTIO_BLK_T_GET_ID: { + size_t size = MIN(iov_size(&elem->in_sg[0], in_num), + VIRTIO_BLK_ID_BYTES); + snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk"); + req->in->status = VIRTIO_BLK_S_OK; + req->size = elem->in_sg[0].iov_len; + break; + } + case VIRTIO_BLK_T_DISCARD: + case VIRTIO_BLK_T_WRITE_ZEROES: { + int rc; + rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], + out_num, type); + if (rc == 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } + break; + } + default: + req->in->status = VIRTIO_BLK_S_UNSUPP; + break; + } + + vu_block_req_complete(req); + return; + +err: + free(elem); + g_free(req); + return; +} + +static void vu_block_process_vq(VuDev *vu_dev, int idx) +{ + VuServer *server; + VuVirtq *vq; + struct req_data *req_data; + + server = container_of(vu_dev, VuServer, vu_dev); + assert(server); + + vq = vu_get_queue(vu_dev, idx); + assert(vq); + VuVirtqElement *elem; + while (1) { + elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + + sizeof(VuBlockReq)); + if (elem) { + req_data = g_new0(struct req_data, 1); + req_data->server = server; + req_data->vq = vq; + req_data->elem = elem; + Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, + req_data); + aio_co_enter(server->ioc->ctx, co); + } else { + break; + } + } +} + +static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +{ + VuVirtq *vq; + + assert(vu_dev); + + vq = vu_get_queue(vu_dev, idx); + vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); +} + +static uint64_t vu_block_get_features(VuDev *dev) +{ + uint64_t features; + VuServer *server = container_of(dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + features = 1ull << VIRTIO_BLK_F_SIZE_MAX | + 1ull << VIRTIO_BLK_F_SEG_MAX | + 1ull << VIRTIO_BLK_F_TOPOLOGY | + 1ull << VIRTIO_BLK_F_BLK_SIZE | + 1ull << VIRTIO_BLK_F_FLUSH | + 1ull << VIRTIO_BLK_F_DISCARD | + 1ull << VIRTIO_BLK_F_WRITE_ZEROES | + 1ull << VIRTIO_BLK_F_CONFIG_WCE | + 1ull << VIRTIO_F_VERSION_1 | + 1ull << VIRTIO_RING_F_INDIRECT_DESC | + 1ull << VIRTIO_RING_F_EVENT_IDX | + 1ull << VHOST_USER_F_PROTOCOL_FEATURES; + + if (!vdev_blk->writable) { + features |= 1ull << VIRTIO_BLK_F_RO; + } + + return features; +} + +static uint64_t vu_block_get_protocol_features(VuDev *dev) +{ + return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | + 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; +} + +static int +vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + memcpy(config, &vdev_blk->blkcfg, len); + + return 0; +} + +static int +vu_block_set_config(VuDev *vu_dev, const uint8_t *data, + uint32_t offset, uint32_t size, uint32_t flags) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + uint8_t wce; + + /* don't support live migration */ + if (flags != VHOST_SET_CONFIG_TYPE_MASTER) { + return -EINVAL; + } + + if (offset != offsetof(struct virtio_blk_config, wce) || + size != 1) { + return -EINVAL; + } + + wce = *data; + vdev_blk->blkcfg.wce = wce; + blk_set_enable_write_cache(vdev_blk->backend, wce); + return 0; +} + +/* + * When the client disconnects, it sends a VHOST_USER_NONE request + * and vu_process_message will simple call exit which cause the VM + * to exit abruptly. + * To avoid this issue, process VHOST_USER_NONE request ahead + * of vu_process_message. + * + */ +static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +{ + if (vmsg->request == VHOST_USER_NONE) { + dev->panic(dev, "disconnect"); + return true; + } + return false; +} + +static const VuDevIface vu_block_iface = { + .get_features = vu_block_get_features, + .queue_set_started = vu_block_queue_set_started, + .get_protocol_features = vu_block_get_protocol_features, + .get_config = vu_block_get_config, + .set_config = vu_block_set_config, + .process_msg = vu_block_process_msg, +}; + +static void blk_aio_attached(AioContext *ctx, void *opaque) +{ + VuBlockDev *vub_dev = opaque; + aio_context_acquire(ctx); + vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); + aio_context_release(ctx); +} + +static void blk_aio_detach(void *opaque) +{ + VuBlockDev *vub_dev = opaque; + AioContext *ctx = vub_dev->vu_server.ctx; + aio_context_acquire(ctx); + vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); + aio_context_release(ctx); +} + +static void +vu_block_initialize_config(BlockDriverState *bs, + struct virtio_blk_config *config, uint32_t blk_size) +{ + config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; + config->blk_size = blk_size; + config->size_max = 0; + config->seg_max = 128 - 2; + config->min_io_size = 1; + config->opt_io_size = 1; + config->num_queues = VHOST_USER_BLK_MAX_QUEUES; + config->max_discard_sectors = 32768; + config->max_discard_seg = 1; + config->discard_sector_alignment = config->blk_size >> 9; + config->max_write_zeroes_sectors = 32768; + config->max_write_zeroes_seg = 1; +} + +static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +{ + + BlockBackend *blk; + Error *local_error = NULL; + const char *node_name = vu_block_device->node_name; + bool writable = vu_block_device->writable; + uint64_t perm = BLK_PERM_CONSISTENT_READ; + int ret; + + AioContext *ctx; + + BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); + + if (!bs) { + error_propagate(errp, local_error); + return NULL; + } + + if (bdrv_is_read_only(bs)) { + writable = false; + } + + if (writable) { + perm |= BLK_PERM_WRITE; + } + + ctx = bdrv_get_aio_context(bs); + aio_context_acquire(ctx); + bdrv_invalidate_cache(bs, NULL); + aio_context_release(ctx); + + /* + * Don't allow resize while the vhost user server is running, + * otherwise we don't care what happens with the node. + */ + blk = blk_new(bdrv_get_aio_context(bs), perm, + BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | + BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); + ret = blk_insert_bs(blk, bs, errp); + + if (ret < 0) { + goto fail; + } + + blk_set_enable_write_cache(blk, false); + + blk_set_allow_aio_context_change(blk, true); + + vu_block_device->blkcfg.wce = 0; + vu_block_device->backend = blk; + if (!vu_block_device->blk_size) { + vu_block_device->blk_size = BDRV_SECTOR_SIZE; + } + vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; + blk_set_guest_block_size(blk, vu_block_device->blk_size); + vu_block_initialize_config(bs, &vu_block_device->blkcfg, + vu_block_device->blk_size); + return vu_block_device; + +fail: + blk_unref(blk); + return NULL; +} + +static void vu_block_deinit(VuBlockDev *vu_block_device) +{ + if (vu_block_device->backend) { + blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, + blk_aio_detach, vu_block_device); + } + + blk_unref(vu_block_device->backend); +} + +static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) +{ + vhost_user_server_stop(&vu_block_device->vu_server); + vu_block_deinit(vu_block_device); +} + +static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, + Error **errp) +{ + AioContext *ctx; + SocketAddress *addr = vu_block_device->addr; + + if (!vu_block_init(vu_block_device, errp)) { + return; + } + + ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); + + if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, + VHOST_USER_BLK_MAX_QUEUES, + NULL, &vu_block_iface, + errp)) { + goto error; + } + + blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, + blk_aio_detach, vu_block_device); + vu_block_device->running = true; + return; + + error: + vu_block_deinit(vu_block_device); +} + +static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) +{ + if (vus->running) { + error_setg(errp, "The property can't be modified " + "while the server is running"); + return false; + } + return true; +} + +static void vu_set_node_name(Object *obj, const char *value, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + if (vus->node_name) { + g_free(vus->node_name); + } + + vus->node_name = g_strdup(value); +} + +static char *vu_get_node_name(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return g_strdup(vus->node_name); +} + +static void free_socket_addr(SocketAddress *addr) +{ + g_free(addr->u.q_unix.path); + g_free(addr); +} + +static void vu_set_unix_socket(Object *obj, const char *value, + Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + if (vus->addr) { + free_socket_addr(vus->addr); + } + + SocketAddress *addr = g_new0(SocketAddress, 1); + addr->type = SOCKET_ADDRESS_TYPE_UNIX; + addr->u.q_unix.path = g_strdup(value); + vus->addr = addr; +} + +static char *vu_get_unix_socket(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return g_strdup(vus->addr->u.q_unix.path); +} + +static bool vu_get_block_writable(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return vus->writable; +} + +static void vu_set_block_writable(Object *obj, bool value, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + vus->writable = value; +} + +static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + uint32_t value = vus->blk_size; + + visit_type_uint32(v, name, &value, errp); +} + +static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + Error *local_err = NULL; + uint32_t value; + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + visit_type_uint32(v, name, &value, &local_err); + if (local_err) { + goto out; + } + + check_block_size(object_get_typename(obj), name, value, &local_err); + if (local_err) { + goto out; + } + + vus->blk_size = value; + +out: + error_propagate(errp, local_err); +} + +static void vhost_user_blk_server_instance_finalize(Object *obj) +{ + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); + + vhost_user_blk_server_stop(vub); + + /* + * Unlike object_property_add_str, object_class_property_add_str + * doesn't have a release method. Thus manual memory freeing is + * needed. + */ + free_socket_addr(vub->addr); + g_free(vub->node_name); +} + +static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) +{ + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); + + vhost_user_blk_server_start(vub, errp); +} + +static void vhost_user_blk_server_class_init(ObjectClass *klass, + void *class_data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); + ucc->complete = vhost_user_blk_server_complete; + + object_class_property_add_bool(klass, "writable", + vu_get_block_writable, + vu_set_block_writable); + + object_class_property_add_str(klass, "node-name", + vu_get_node_name, + vu_set_node_name); + + object_class_property_add_str(klass, "unix-socket", + vu_get_unix_socket, + vu_set_unix_socket); + + object_class_property_add(klass, "logical-block-size", "uint32", + vu_get_blk_size, vu_set_blk_size, + NULL, NULL); +} + +static const TypeInfo vhost_user_blk_server_info = { + .name = TYPE_VHOST_USER_BLK_SERVER, + .parent = TYPE_OBJECT, + .instance_size = sizeof(VuBlockDev), + .instance_finalize = vhost_user_blk_server_instance_finalize, + .class_init = vhost_user_blk_server_class_init, + .interfaces = (InterfaceInfo[]) { + {TYPE_USER_CREATABLE}, + {} + }, +}; + +static void vhost_user_blk_server_register_types(void) +{ + type_register_static(&vhost_user_blk_server_info); +} + +type_init(vhost_user_blk_server_register_types) diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ static bool object_create_initial(const char *type, QemuOpts *opts) } #endif + /* Reason: vhost-user-blk-server property "node-name" */ + if (g_str_equal(type, "vhost-user-blk-server")) { + return false; + } /* * Reason: filter-* property "netdev" etc. */ diff --git a/block/meson.build b/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/meson.build +++ b/block/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Suggested-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-8-coiby.xu@gmail.com [Removed reference to vhost-user-blk-test.c, it will be sent in a separate pull request. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-block@nongnu.org S: Supported F: tests/image-fuzzer/ +Vhost-user block device backend server +M: Coiby Xu <Coiby.Xu@gmail.com> +S: Maintained +F: block/export/vhost-user-blk-server.c +F: util/vhost-user-server.c +F: tests/qtest/libqos/vhost-user-blk.c + Replication M: Wen Congyang <wencongyang2@huawei.com> M: Xie Changlong <xiechanglong.d@gmail.com> -- 2.26.2 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, return false; } - /* zero out unspecified fileds */ + /* zero out unspecified fields */ *server = (VuServer) { .listener = listener, .vu_iface = vu_iface, -- 2.26.2 We already have access to the value with the correct type (ioc and sioc are the same QIOChannel). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-4-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, server->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(server->ioc)); qio_channel_attach_aio_context(server->ioc, server->ctx); - qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); + qio_channel_set_blocking(server->ioc, false, NULL); vu_client_start(server); } -- 2.26.2 Explicitly deleting watches is not necessary since libvhost-user calls remove_watch() during vu_deinit(). Add an assertion to check this though. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) /* When this is set vu_client_trip will stop new processing vhost-user message */ server->sioc = NULL; - VuFdWatch *vu_fd_watch, *next; - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, - NULL, NULL, NULL); - } - - while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - if (!vu_fd_watch->processing) { - QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); - g_free(vu_fd_watch); - } - } - } - while (server->processing_msg) { if (server->ioc->read_coroutine) { server->ioc->read_coroutine = NULL; @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) } vu_deinit(&server->vu_dev); + + /* vu_deinit() should have called remove_watch() */ + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); + object_unref(OBJECT(sioc)); object_unref(OBJECT(server->ioc)); } -- 2.26.2 Only one struct is needed per request. Drop req_data and the separate VuBlockReq instance. Instead let vu_queue_pop() allocate everything at once. This fixes the req_data memory leak in vu_block_virtio_process_req(). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-6-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.c | 68 +++++++++------------------- 1 file changed, 21 insertions(+), 47 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { }; typedef struct VuBlockReq { - VuVirtqElement *elem; + VuVirtqElement elem; int64_t sector_num; size_t size; struct virtio_blk_inhdr *in; @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) VuDev *vu_dev = &req->server->vu_dev; /* IO size with 1 extra status byte */ - vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); + vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1); vu_queue_notify(vu_dev, req->vq); - if (req->elem) { - free(req->elem); - } - - g_free(req); + free(req); } static VuBlockDev *get_vu_block_device_by_server(VuServer *server) @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_flush(VuBlockReq *req) blk_co_flush(backend); } -struct req_data { - VuServer *server; - VuVirtq *vq; - VuVirtqElement *elem; -}; - static void coroutine_fn vu_block_virtio_process_req(void *opaque) { - struct req_data *data = opaque; - VuServer *server = data->server; - VuVirtq *vq = data->vq; - VuVirtqElement *elem = data->elem; + VuBlockReq *req = opaque; + VuServer *server = req->server; + VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockReq *req; VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); BlockBackend *backend = vdev_blk->backend; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) struct iovec *out_iov = elem->out_sg; unsigned in_num = elem->in_num; unsigned out_num = elem->out_num; + /* refer to hw/block/virtio_blk.c */ if (elem->out_num < 1 || elem->in_num < 1) { error_report("virtio-blk request missing headers"); - free(elem); - return; + goto err; } - req = g_new0(VuBlockReq, 1); - req->server = server; - req->vq = vq; - req->elem = elem; - if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, sizeof(req->out)) != sizeof(req->out))) { error_report("virtio-blk request outhdr too short"); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) err: free(elem); - g_free(req); - return; } static void vu_block_process_vq(VuDev *vu_dev, int idx) { - VuServer *server; - VuVirtq *vq; - struct req_data *req_data; + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuVirtq *vq = vu_get_queue(vu_dev, idx); - server = container_of(vu_dev, VuServer, vu_dev); - assert(server); - - vq = vu_get_queue(vu_dev, idx); - assert(vq); - VuVirtqElement *elem; while (1) { - elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + - sizeof(VuBlockReq)); - if (elem) { - req_data = g_new0(struct req_data, 1); - req_data->server = server; - req_data->vq = vq; - req_data->elem = elem; - Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, - req_data); - aio_co_enter(server->ioc->ctx, co); - } else { + VuBlockReq *req; + + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + if (!req) { break; } + + req->server = server; + req->vq = vq; + + Coroutine *co = + qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_enter(co); } } -- 2.26.2 The device panic notifier callback is not used. Drop it. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-7-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 3 --- block/export/vhost-user-blk-server.c | 3 +-- util/vhost-user-server.c | 6 ------ 3 files changed, 1 insertion(+), 11 deletions(-) diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.h +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ typedef struct VuFdWatch { } VuFdWatch; typedef struct VuServer VuServer; -typedef void DevicePanicNotifierFn(VuServer *server); struct VuServer { QIONetListener *listener; AioContext *ctx; - DevicePanicNotifierFn *device_panic_notifier; int max_queues; const VuDevIface *vu_iface; VuDev vu_dev; @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, SocketAddress *unix_socket, AioContext *ctx, uint16_t max_queues, - DevicePanicNotifierFn *device_panic_notifier, const VuDevIface *vu_iface, Error **errp); diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, - NULL, &vu_block_iface, + VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, errp)) { goto error; } diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void panic_cb(VuDev *vu_dev, const char *buf) close_client(server); } - if (server->device_panic_notifier) { - server->device_panic_notifier(server); - } - /* * Set the callback function for network listener so another * vhost-user client can connect to this server @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, SocketAddress *socket_addr, AioContext *ctx, uint16_t max_queues, - DevicePanicNotifierFn *device_panic_notifier, const VuDevIface *vu_iface, Error **errp) { @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, .vu_iface = vu_iface, .max_queues = max_queues, .ctx = ctx, - .device_panic_notifier = device_panic_notifier, }; qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); -- 2.26.2 fds[] is leaked when qio_channel_readv_full() fails. Use vmsg->fds[] instead of keeping a local fds[] array. Then we can reuse goto fail to clean up fds. vmsg->fd_num must be zeroed before the loop to make this safe. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-8-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 50 ++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 27 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) }; int rc, read_bytes = 0; Error *local_err = NULL; - /* - * Store fds/nfds returned from qio_channel_readv_full into - * temporary variables. - * - * VhostUserMsg is a packed structure, gcc will complain about passing - * pointer to a packed structure member if we pass &VhostUserMsg.fd_num - * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, - * thus two temporary variables nfds and fds are used here. - */ - size_t nfds = 0, nfds_t = 0; const size_t max_fds = G_N_ELEMENTS(vmsg->fds); - int *fds_t = NULL; VuServer *server = container_of(vu_dev, VuServer, vu_dev); QIOChannel *ioc = server->ioc; + vmsg->fd_num = 0; if (!ioc) { error_report_err(local_err); goto fail; @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) assert(qemu_in_coroutine()); do { + size_t nfds = 0; + int *fds = NULL; + /* * qio_channel_readv_full may have short reads, keeping calling it * until getting VHOST_USER_HDR_SIZE or 0 bytes in total */ - rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); + rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err); if (rc < 0) { if (rc == QIO_CHANNEL_ERR_BLOCK) { + assert(local_err == NULL); qio_channel_yield(ioc, G_IO_IN); continue; } else { error_report_err(local_err); - return false; + goto fail; } } - read_bytes += rc; - if (nfds_t > 0) { - if (nfds + nfds_t > max_fds) { + + if (nfds > 0) { + if (vmsg->fd_num + nfds > max_fds) { error_report("A maximum of %zu fds are allowed, " "however got %zu fds now", - max_fds, nfds + nfds_t); + max_fds, vmsg->fd_num + nfds); + g_free(fds); goto fail; } - memcpy(vmsg->fds + nfds, fds_t, - nfds_t *sizeof(vmsg->fds[0])); - nfds += nfds_t; - g_free(fds_t); + memcpy(vmsg->fds + vmsg->fd_num, fds, nfds * sizeof(vmsg->fds[0])); + vmsg->fd_num += nfds; + g_free(fds); } - if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { - break; + + if (rc == 0) { /* socket closed */ + goto fail; } - iov.iov_base = (char *)vmsg + read_bytes; - iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; - } while (true); - vmsg->fd_num = nfds; + iov.iov_base += rc; + iov.iov_len -= rc; + read_bytes += rc; + } while (read_bytes != VHOST_USER_HDR_SIZE); + /* qio_channel_readv_full will make socket fds blocking, unblock them */ vmsg_unblock_fds(vmsg); if (vmsg->size > sizeof(vmsg->payload)) { -- 2.26.2 Unexpected EOF is an error that must be reported. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-9-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) }; if (vmsg->size) { rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); - if (rc == -1) { - error_report_err(local_err); + if (rc != 1) { + if (local_err) { + error_report_err(local_err); + } goto fail; } } -- 2.26.2 The vu_client_trip() coroutine is leaked during AioContext switching. It is also unsafe to destroy the vu_dev in panic_cb() since its callers still access it in some cases. Rework the lifecycle to solve these safety issues. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-10-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 29 ++-- block/export/vhost-user-blk-server.c | 9 +- util/vhost-user-server.c | 245 +++++++++++++++------------ 3 files changed, 155 insertions(+), 128 deletions(-) diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.h +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "standard-headers/linux/virtio_blk.h" +/* A kick fd that we monitor on behalf of libvhost-user */ typedef struct VuFdWatch { VuDev *vu_dev; int fd; /*kick fd*/ void *pvt; vu_watch_cb cb; - bool processing; QTAILQ_ENTRY(VuFdWatch) next; } VuFdWatch; -typedef struct VuServer VuServer; - -struct VuServer { +/** + * VuServer: + * A vhost-user server instance with user-defined VuDevIface callbacks. + * Vhost-user device backends can be implemented using VuServer. VuDevIface + * callbacks and virtqueue kicks run in the given AioContext. + */ +typedef struct { QIONetListener *listener; + QEMUBH *restart_listener_bh; AioContext *ctx; int max_queues; const VuDevIface *vu_iface; + + /* Protected by ctx lock */ VuDev vu_dev; QIOChannel *ioc; /* The I/O channel with the client */ QIOChannelSocket *sioc; /* The underlying data channel with the client */ - /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ - QIOChannel *ioc_slave; - QIOChannelSocket *sioc_slave; - Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; - /* restart coroutine co_trip if AIOContext is changed */ - bool aio_context_changed; - bool processing_msg; -}; + + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ +} VuServer; bool vhost_user_server_start(VuServer *server, SocketAddress *unix_socket, @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, void vhost_user_server_stop(VuServer *server); -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx); +void vhost_user_server_detach_aio_context(VuServer *server); #endif /* VHOST_USER_SERVER_H */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_block_iface = { static void blk_aio_attached(AioContext *ctx, void *opaque) { VuBlockDev *vub_dev = opaque; - aio_context_acquire(ctx); - vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); - aio_context_release(ctx); + vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); } static void blk_aio_detach(void *opaque) { VuBlockDev *vub_dev = opaque; - AioContext *ctx = vub_dev->vu_server.ctx; - aio_context_acquire(ctx); - vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); - aio_context_release(ctx); + vhost_user_server_detach_aio_context(&vub_dev->vu_server); } static void diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "block/aio-wait.h" #include "vhost-user-server.h" +/* + * Theory of operation: + * + * VuServer is started and stopped by vhost_user_server_start() and + * vhost_user_server_stop() from the main loop thread. Starting the server + * opens a vhost-user UNIX domain socket and listens for incoming connections. + * Only one connection is allowed at a time. + * + * The connection is handled by the vu_client_trip() coroutine in the + * VuServer->ctx AioContext. The coroutine consists of a vu_dispatch() loop + * where libvhost-user calls vu_message_read() to receive the next vhost-user + * protocol messages over the UNIX domain socket. + * + * When virtqueues are set up libvhost-user calls set_watch() to monitor kick + * fds. These fds are also handled in the VuServer->ctx AioContext. + * + * Both vu_client_trip() and kick fd monitoring can be stopped by shutting down + * the socket connection. Shutting down the socket connection causes + * vu_message_read() to fail since no more data can be received from the socket. + * After vu_dispatch() fails, vu_client_trip() calls vu_deinit() to stop + * libvhost-user before terminating the coroutine. vu_deinit() calls + * remove_watch() to stop monitoring kick fds and this stops virtqueue + * processing. + * + * When vu_client_trip() has finished cleaning up it schedules a BH in the main + * loop thread to accept the next client connection. + * + * When libvhost-user detects an error it calls panic_cb() and sets the + * dev->broken flag. Both vu_client_trip() and kick fd processing stop when + * the dev->broken flag is set. + * + * It is possible to switch AioContexts using + * vhost_user_server_detach_aio_context() and + * vhost_user_server_attach_aio_context(). They stop monitoring fds in the old + * AioContext and resume monitoring in the new AioContext. The vu_client_trip() + * coroutine remains in a yielded state during the switch. This is made + * possible by QIOChannel's support for spurious coroutine re-entry in + * qio_channel_yield(). The coroutine will restart I/O when re-entered from the + * new AioContext. + */ + static void vmsg_close_fds(VhostUserMsg *vmsg) { int i; @@ -XXX,XX +XXX,XX @@ static void vmsg_unblock_fds(VhostUserMsg *vmsg) } } -static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, - gpointer opaque); - -static void close_client(VuServer *server) -{ - /* - * Before closing the client - * - * 1. Let vu_client_trip stop processing new vhost-user msg - * - * 2. remove kick_handler - * - * 3. wait for the kick handler to be finished - * - * 4. wait for the current vhost-user msg to be finished processing - */ - - QIOChannelSocket *sioc = server->sioc; - /* When this is set vu_client_trip will stop new processing vhost-user message */ - server->sioc = NULL; - - while (server->processing_msg) { - if (server->ioc->read_coroutine) { - server->ioc->read_coroutine = NULL; - qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, - NULL, server->ioc); - server->processing_msg = false; - } - } - - vu_deinit(&server->vu_dev); - - /* vu_deinit() should have called remove_watch() */ - assert(QTAILQ_EMPTY(&server->vu_fd_watches)); - - object_unref(OBJECT(sioc)); - object_unref(OBJECT(server->ioc)); -} - static void panic_cb(VuDev *vu_dev, const char *buf) { - VuServer *server = container_of(vu_dev, VuServer, vu_dev); - - /* avoid while loop in close_client */ - server->processing_msg = false; - - if (buf) { - error_report("vu_panic: %s", buf); - } - - if (server->sioc) { - close_client(server); - } - - /* - * Set the callback function for network listener so another - * vhost-user client can connect to this server - */ - qio_net_listener_set_client_func(server->listener, - vu_accept, - server, - NULL); + error_report("vu_panic: %s", buf); } static bool coroutine_fn @@ -XXX,XX +XXX,XX @@ fail: return false; } - -static void vu_client_start(VuServer *server); static coroutine_fn void vu_client_trip(void *opaque) { VuServer *server = opaque; + VuDev *vu_dev = &server->vu_dev; - while (!server->aio_context_changed && server->sioc) { - server->processing_msg = true; - vu_dispatch(&server->vu_dev); - server->processing_msg = false; + while (!vu_dev->broken && vu_dispatch(vu_dev)) { + /* Keep running */ } - if (server->aio_context_changed && server->sioc) { - server->aio_context_changed = false; - vu_client_start(server); - } -} + vu_deinit(vu_dev); + + /* vu_deinit() should have called remove_watch() */ + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); + + object_unref(OBJECT(server->sioc)); + server->sioc = NULL; -static void vu_client_start(VuServer *server) -{ - server->co_trip = qemu_coroutine_create(vu_client_trip, server); - aio_co_enter(server->ctx, server->co_trip); + object_unref(OBJECT(server->ioc)); + server->ioc = NULL; + + server->co_trip = NULL; + if (server->restart_listener_bh) { + qemu_bh_schedule(server->restart_listener_bh); + } + aio_wait_kick(); } /* @@ -XXX,XX +XXX,XX @@ static void vu_client_start(VuServer *server) static void kick_handler(void *opaque) { VuFdWatch *vu_fd_watch = opaque; - vu_fd_watch->processing = true; - vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); - vu_fd_watch->processing = false; + VuDev *vu_dev = vu_fd_watch->vu_dev; + + vu_fd_watch->cb(vu_dev, 0, vu_fd_watch->pvt); + + /* Stop vu_client_trip() if an error occurred in vu_fd_watch->cb() */ + if (vu_dev->broken) { + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + } } - static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) { @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); server->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(server->ioc)); - qio_channel_attach_aio_context(server->ioc, server->ctx); + + /* TODO vu_message_write() spins if non-blocking! */ qio_channel_set_blocking(server->ioc, false, NULL); - vu_client_start(server); + + server->co_trip = qemu_coroutine_create(vu_client_trip, server); + + aio_context_acquire(server->ctx); + vhost_user_server_attach_aio_context(server, server->ctx); + aio_context_release(server->ctx); } - void vhost_user_server_stop(VuServer *server) { + aio_context_acquire(server->ctx); + + qemu_bh_delete(server->restart_listener_bh); + server->restart_listener_bh = NULL; + if (server->sioc) { - close_client(server); + VuFdWatch *vu_fd_watch; + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, + NULL, NULL, NULL, vu_fd_watch); + } + + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + + AIO_WAIT_WHILE(server->ctx, server->co_trip); } + aio_context_release(server->ctx); + if (server->listener) { qio_net_listener_disconnect(server->listener); object_unref(OBJECT(server->listener)); } +} + +/* + * Allow the next client to connect to the server. Called from a BH in the main + * loop. + */ +static void restart_listener_bh(void *opaque) +{ + VuServer *server = opaque; + qio_net_listener_set_client_func(server->listener, vu_accept, server, + NULL); } -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) +/* Called with ctx acquired */ +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx) { - VuFdWatch *vu_fd_watch, *next; - void *opaque = NULL; - IOHandler *io_read = NULL; - bool attach; + VuFdWatch *vu_fd_watch; - server->ctx = ctx ? ctx : qemu_get_aio_context(); + server->ctx = ctx; if (!server->sioc) { - /* not yet serving any client*/ return; } - if (ctx) { - qio_channel_attach_aio_context(server->ioc, ctx); - server->aio_context_changed = true; - io_read = kick_handler; - attach = true; - } else { + qio_channel_attach_aio_context(server->ioc, ctx); + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, kick_handler, NULL, + NULL, vu_fd_watch); + } + + aio_co_schedule(ctx, server->co_trip); +} + +/* Called with server->ctx acquired */ +void vhost_user_server_detach_aio_context(VuServer *server) +{ + if (server->sioc) { + VuFdWatch *vu_fd_watch; + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, + NULL, NULL, NULL, vu_fd_watch); + } + qio_channel_detach_aio_context(server->ioc); - /* server->ioc->ctx keeps the old AioConext */ - ctx = server->ioc->ctx; - attach = false; } - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - if (vu_fd_watch->cb) { - opaque = attach ? vu_fd_watch : NULL; - aio_set_fd_handler(ctx, vu_fd_watch->fd, true, - io_read, NULL, NULL, - opaque); - } - } + server->ctx = NULL; } - bool vhost_user_server_start(VuServer *server, SocketAddress *socket_addr, AioContext *ctx, @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, const VuDevIface *vu_iface, Error **errp) { + QEMUBH *bh; QIONetListener *listener = qio_net_listener_new(); if (qio_net_listener_open_sync(listener, socket_addr, 1, errp) < 0) { @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, return false; } + bh = qemu_bh_new(restart_listener_bh, server); + /* zero out unspecified fields */ *server = (VuServer) { .listener = listener, + .restart_listener_bh = bh, .vu_iface = vu_iface, .max_queues = max_queues, .ctx = ctx, -- 2.26.2 Propagate the flush return value since errors are possible. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-11-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static void coroutine_fn vu_block_flush(VuBlockReq *req) +static int coroutine_fn vu_block_flush(VuBlockReq *req) { VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); BlockBackend *backend = vdev_blk->backend; - blk_co_flush(backend); + return blk_co_flush(backend); } static void coroutine_fn vu_block_virtio_process_req(void *opaque) @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - vu_block_flush(req); - req->in->status = VIRTIO_BLK_S_OK; + if (vu_block_flush(req) == 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } break; case VIRTIO_BLK_T_GET_ID: { size_t size = MIN(iov_size(&elem->in_sg[0], in_num), -- 2.26.2 Use the new QAPI block exports API instead of defining our own QOM objects. This is a large change because the lifecycle of VuBlockDev needs to follow BlockExportDriver. QOM properties are replaced by QAPI options objects. VuBlockDev is renamed VuBlkExport and contains a BlockExport field. Several fields can be dropped since BlockExport already has equivalents. The file names and meson build integration will be adjusted in a future patch. libvhost-user should probably be built as a static library that is linked into QEMU instead of as a .c file that results in duplicate compilation. The new command-line syntax is: $ qemu-storage-daemon \ --blockdev file,node-name=drive0,filename=test.img \ --export vhost-user-blk,node-name=drive0,id=export0,unix-socket=/tmp/vhost-user-blk.sock Note that unix-socket is optional because we may wish to accept chardevs too in the future. Markus noted that supported address families are not explicit in the QAPI schema. It is unlikely that support for more address families will be added since file descriptor passing is required and few address families support it. If a new address family needs to be added, then the QAPI 'features' syntax can be used to advertize them. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20200924151549.913737-12-stefanha@redhat.com [Skip test on big-endian host architectures because this device doesn't support them yet (as already mentioned in a code comment). --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 21 +- block/export/vhost-user-blk-server.h | 23 +- block/export/export.c | 6 + block/export/vhost-user-blk-server.c | 452 +++++++-------------------- util/vhost-user-server.c | 10 +- block/export/meson.build | 1 + block/meson.build | 1 - 7 files changed, 156 insertions(+), 358 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ 'data': { '*name': 'str', '*description': 'str', '*bitmap': 'str' } } +## +# @BlockExportOptionsVhostUserBlk: +# +# A vhost-user-blk block export. +# +# @addr: The vhost-user socket on which to listen. Both 'unix' and 'fd' +# SocketAddress types are supported. Passed fds must be UNIX domain +# sockets. +# @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. +# +# Since: 5.2 +## +{ 'struct': 'BlockExportOptionsVhostUserBlk', + 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } + ## # @NbdServerAddOptions: # @@ -XXX,XX +XXX,XX @@ # An enumeration of block export types # # @nbd: NBD export +# @vhost-user-blk: vhost-user-blk export (since 5.2) # # Since: 4.2 ## { 'enum': 'BlockExportType', - 'data': [ 'nbd' ] } + 'data': [ 'nbd', 'vhost-user-blk' ] } ## # @BlockExportOptions: @@ -XXX,XX +XXX,XX @@ '*writethrough': 'bool' }, 'discriminator': 'type', 'data': { - 'nbd': 'BlockExportOptionsNbd' + 'nbd': 'BlockExportOptionsNbd', + 'vhost-user-blk': 'BlockExportOptionsVhostUserBlk' } } ## diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.h +++ b/block/export/vhost-user-blk-server.h @@ -XXX,XX +XXX,XX @@ #ifndef VHOST_USER_BLK_SERVER_H #define VHOST_USER_BLK_SERVER_H -#include "util/vhost-user-server.h" -typedef struct VuBlockDev VuBlockDev; -#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" -#define VHOST_USER_BLK_SERVER(obj) \ - OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) +#include "block/export.h" -/* vhost user block device */ -struct VuBlockDev { - Object parent_obj; - char *node_name; - SocketAddress *addr; - AioContext *ctx; - VuServer vu_server; - bool running; - uint32_t blk_size; - BlockBackend *backend; - QIOChannelSocket *sioc; - QTAILQ_ENTRY(VuBlockDev) next; - struct virtio_blk_config blkcfg; - bool writable; -}; +/* For block/export/export.c */ +extern const BlockExportDriver blk_exp_vhost_user_blk; #endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" +#if CONFIG_LINUX +#include "block/export/vhost-user-blk-server.h" +#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, +#if CONFIG_LINUX + &blk_exp_vhost_user_blk, +#endif }; /* Only accessed from the main thread */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "block/block.h" +#include "contrib/libvhost-user/libvhost-user.h" +#include "standard-headers/linux/virtio_blk.h" +#include "util/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { unsigned char status; }; -typedef struct VuBlockReq { +typedef struct VuBlkReq { VuVirtqElement elem; int64_t sector_num; size_t size; @@ -XXX,XX +XXX,XX @@ typedef struct VuBlockReq { struct virtio_blk_outhdr out; VuServer *server; struct VuVirtq *vq; -} VuBlockReq; +} VuBlkReq; -static void vu_block_req_complete(VuBlockReq *req) +/* vhost user block device */ +typedef struct { + BlockExport export; + VuServer vu_server; + uint32_t blk_size; + QIOChannelSocket *sioc; + struct virtio_blk_config blkcfg; + bool writable; +} VuBlkExport; + +static void vu_blk_req_complete(VuBlkReq *req) { VuDev *vu_dev = &req->server->vu_dev; @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) free(req); } -static VuBlockDev *get_vu_block_device_by_server(VuServer *server) -{ - return container_of(server, VuBlockDev, vu_server); -} - static int coroutine_fn -vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, - uint32_t iovcnt, uint32_t type) +vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov, + uint32_t iovcnt, uint32_t type) { struct virtio_blk_discard_write_zeroes desc; ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, le32_to_cpu(desc.num_sectors) << 9 }; if (type == VIRTIO_BLK_T_DISCARD) { - if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { return 0; } } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { - if (blk_co_pwrite_zeroes(vdev_blk->backend, - range[0], range[1], 0) == 0) { + if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) { return 0; } } @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static int coroutine_fn vu_block_flush(VuBlockReq *req) +static void coroutine_fn vu_blk_virtio_process_req(void *opaque) { - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); - BlockBackend *backend = vdev_blk->backend; - return blk_co_flush(backend); -} - -static void coroutine_fn vu_block_virtio_process_req(void *opaque) -{ - VuBlockReq *req = opaque; + VuBlkReq *req = opaque; VuServer *server = req->server; VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - BlockBackend *backend = vdev_blk->backend; + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + BlockBackend *blk = vexp->export.blk; struct iovec *in_iov = elem->in_sg; struct iovec *out_iov = elem->out_sg; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) bool is_write = type & VIRTIO_BLK_T_OUT; req->sector_num = le64_to_cpu(req->out.sector); - int64_t offset = req->sector_num * vdev_blk->blk_size; + if (is_write && !vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + int64_t offset = req->sector_num * vexp->blk_size; QEMUIOVector qiov; if (is_write) { qemu_iovec_init_external(&qiov, out_iov, out_num); - ret = blk_co_pwritev(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); } else { qemu_iovec_init_external(&qiov, in_iov, in_num); - ret = blk_co_preadv(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0); } if (ret >= 0) { req->in->status = VIRTIO_BLK_S_OK; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - if (vu_block_flush(req) == 0) { + if (blk_co_flush(blk) == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { req->in->status = VIRTIO_BLK_S_IOERR; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) case VIRTIO_BLK_T_DISCARD: case VIRTIO_BLK_T_WRITE_ZEROES: { int rc; - rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], - out_num, type); + + if (!vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); if (rc == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } - vu_block_req_complete(req); + vu_blk_req_complete(req); return; err: - free(elem); + free(req); } -static void vu_block_process_vq(VuDev *vu_dev, int idx) +static void vu_blk_process_vq(VuDev *vu_dev, int idx) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); VuVirtq *vq = vu_get_queue(vu_dev, idx); while (1) { - VuBlockReq *req; + VuBlkReq *req; - req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq)); if (!req) { break; } @@ -XXX,XX +XXX,XX @@ static void vu_block_process_vq(VuDev *vu_dev, int idx) req->vq = vq; Coroutine *co = - qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_create(vu_blk_virtio_process_req, req); qemu_coroutine_enter(co); } } -static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started) { VuVirtq *vq; assert(vu_dev); vq = vu_get_queue(vu_dev, idx); - vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); + vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL); } -static uint64_t vu_block_get_features(VuDev *dev) +static uint64_t vu_blk_get_features(VuDev *dev) { uint64_t features; VuServer *server = container_of(dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); features = 1ull << VIRTIO_BLK_F_SIZE_MAX | 1ull << VIRTIO_BLK_F_SEG_MAX | 1ull << VIRTIO_BLK_F_TOPOLOGY | @@ -XXX,XX +XXX,XX @@ static uint64_t vu_block_get_features(VuDev *dev) 1ull << VIRTIO_RING_F_EVENT_IDX | 1ull << VHOST_USER_F_PROTOCOL_FEATURES; - if (!vdev_blk->writable) { + if (!vexp->writable) { features |= 1ull << VIRTIO_BLK_F_RO; } return features; } -static uint64_t vu_block_get_protocol_features(VuDev *dev) +static uint64_t vu_blk_get_protocol_features(VuDev *dev) { return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; } static int -vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +vu_blk_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) { + /* TODO blkcfg must be little-endian for VIRTIO 1.0 */ VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - memcpy(config, &vdev_blk->blkcfg, len); - + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + memcpy(config, &vexp->blkcfg, len); return 0; } static int -vu_block_set_config(VuDev *vu_dev, const uint8_t *data, +vu_blk_set_config(VuDev *vu_dev, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); uint8_t wce; /* don't support live migration */ @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, } wce = *data; - vdev_blk->blkcfg.wce = wce; - blk_set_enable_write_cache(vdev_blk->backend, wce); + vexp->blkcfg.wce = wce; + blk_set_enable_write_cache(vexp->export.blk, wce); return 0; } @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, * of vu_process_message. * */ -static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +static int vu_blk_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) { if (vmsg->request == VHOST_USER_NONE) { dev->panic(dev, "disconnect"); @@ -XXX,XX +XXX,XX @@ static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) return false; } -static const VuDevIface vu_block_iface = { - .get_features = vu_block_get_features, - .queue_set_started = vu_block_queue_set_started, - .get_protocol_features = vu_block_get_protocol_features, - .get_config = vu_block_get_config, - .set_config = vu_block_set_config, - .process_msg = vu_block_process_msg, +static const VuDevIface vu_blk_iface = { + .get_features = vu_blk_get_features, + .queue_set_started = vu_blk_queue_set_started, + .get_protocol_features = vu_blk_get_protocol_features, + .get_config = vu_blk_get_config, + .set_config = vu_blk_set_config, + .process_msg = vu_blk_process_msg, }; static void blk_aio_attached(AioContext *ctx, void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); + VuBlkExport *vexp = opaque; + vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_detach_aio_context(&vub_dev->vu_server); + VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); } static void -vu_block_initialize_config(BlockDriverState *bs, +vu_blk_initialize_config(BlockDriverState *bs, struct virtio_blk_config *config, uint32_t blk_size) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; @@ -XXX,XX +XXX,XX @@ vu_block_initialize_config(BlockDriverState *bs, config->max_write_zeroes_seg = 1; } -static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +static void vu_blk_exp_request_shutdown(BlockExport *exp) { + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - BlockBackend *blk; - Error *local_error = NULL; - const char *node_name = vu_block_device->node_name; - bool writable = vu_block_device->writable; - uint64_t perm = BLK_PERM_CONSISTENT_READ; - int ret; - - AioContext *ctx; - - BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); - - if (!bs) { - error_propagate(errp, local_error); - return NULL; - } - - if (bdrv_is_read_only(bs)) { - writable = false; - } - - if (writable) { - perm |= BLK_PERM_WRITE; - } - - ctx = bdrv_get_aio_context(bs); - aio_context_acquire(ctx); - bdrv_invalidate_cache(bs, NULL); - aio_context_release(ctx); - - /* - * Don't allow resize while the vhost user server is running, - * otherwise we don't care what happens with the node. - */ - blk = blk_new(bdrv_get_aio_context(bs), perm, - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | - BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); - ret = blk_insert_bs(blk, bs, errp); - - if (ret < 0) { - goto fail; - } - - blk_set_enable_write_cache(blk, false); - - blk_set_allow_aio_context_change(blk, true); - - vu_block_device->blkcfg.wce = 0; - vu_block_device->backend = blk; - if (!vu_block_device->blk_size) { - vu_block_device->blk_size = BDRV_SECTOR_SIZE; - } - vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; - blk_set_guest_block_size(blk, vu_block_device->blk_size); - vu_block_initialize_config(bs, &vu_block_device->blkcfg, - vu_block_device->blk_size); - return vu_block_device; - -fail: - blk_unref(blk); - return NULL; -} - -static void vu_block_deinit(VuBlockDev *vu_block_device) -{ - if (vu_block_device->backend) { - blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - } - - blk_unref(vu_block_device->backend); -} - -static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) -{ - vhost_user_server_stop(&vu_block_device->vu_server); - vu_block_deinit(vu_block_device); -} - -static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, - Error **errp) -{ - AioContext *ctx; - SocketAddress *addr = vu_block_device->addr; - - if (!vu_block_init(vu_block_device, errp)) { - return; - } - - ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); - - if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, - errp)) { - goto error; - } - - blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - vu_block_device->running = true; - return; - - error: - vu_block_deinit(vu_block_device); -} - -static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) -{ - if (vus->running) { - error_setg(errp, "The property can't be modified " - "while the server is running"); - return false; - } - return true; -} - -static void vu_set_node_name(Object *obj, const char *value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->node_name) { - g_free(vus->node_name); - } - - vus->node_name = g_strdup(value); -} - -static char *vu_get_node_name(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->node_name); -} - -static void free_socket_addr(SocketAddress *addr) -{ - g_free(addr->u.q_unix.path); - g_free(addr); -} - -static void vu_set_unix_socket(Object *obj, const char *value, - Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->addr) { - free_socket_addr(vus->addr); - } - - SocketAddress *addr = g_new0(SocketAddress, 1); - addr->type = SOCKET_ADDRESS_TYPE_UNIX; - addr->u.q_unix.path = g_strdup(value); - vus->addr = addr; + vhost_user_server_stop(&vexp->vu_server); } -static char *vu_get_unix_socket(Object *obj, Error **errp) +static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, + Error **errp) { - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->addr->u.q_unix.path); -} - -static bool vu_get_block_writable(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return vus->writable; -} - -static void vu_set_block_writable(Object *obj, bool value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - vus->writable = value; -} - -static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - uint32_t value = vus->blk_size; - - visit_type_uint32(v, name, &value, errp); -} - -static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); + BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; Error *local_err = NULL; - uint32_t value; + uint64_t logical_block_size; - if (!vu_prop_modifiable(vus, errp)) { - return; - } + vexp->writable = opts->writable; + vexp->blkcfg.wce = 0; - visit_type_uint32(v, name, &value, &local_err); - if (local_err) { - goto out; + if (vu_opts->has_logical_block_size) { + logical_block_size = vu_opts->logical_block_size; + } else { + logical_block_size = BDRV_SECTOR_SIZE; } - - check_block_size(object_get_typename(obj), name, value, &local_err); + check_block_size(exp->id, "logical-block-size", logical_block_size, + &local_err); if (local_err) { - goto out; + error_propagate(errp, local_err); + return -EINVAL; + } + vexp->blk_size = logical_block_size; + blk_set_guest_block_size(exp->blk, logical_block_size); + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, + logical_block_size); + + blk_set_allow_aio_context_change(exp->blk, true); + blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); + + if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, + VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, + errp)) { + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, + blk_aio_detach, vexp); + return -EADDRNOTAVAIL; } - vus->blk_size = value; - -out: - error_propagate(errp, local_err); -} - -static void vhost_user_blk_server_instance_finalize(Object *obj) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_stop(vub); - - /* - * Unlike object_property_add_str, object_class_property_add_str - * doesn't have a release method. Thus manual memory freeing is - * needed. - */ - free_socket_addr(vub->addr); - g_free(vub->node_name); -} - -static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_start(vub, errp); + return 0; } -static void vhost_user_blk_server_class_init(ObjectClass *klass, - void *class_data) +static void vu_blk_exp_delete(BlockExport *exp) { - UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); - ucc->complete = vhost_user_blk_server_complete; - - object_class_property_add_bool(klass, "writable", - vu_get_block_writable, - vu_set_block_writable); - - object_class_property_add_str(klass, "node-name", - vu_get_node_name, - vu_set_node_name); - - object_class_property_add_str(klass, "unix-socket", - vu_get_unix_socket, - vu_set_unix_socket); + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - object_class_property_add(klass, "logical-block-size", "uint32", - vu_get_blk_size, vu_set_blk_size, - NULL, NULL); + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); } -static const TypeInfo vhost_user_blk_server_info = { - .name = TYPE_VHOST_USER_BLK_SERVER, - .parent = TYPE_OBJECT, - .instance_size = sizeof(VuBlockDev), - .instance_finalize = vhost_user_blk_server_instance_finalize, - .class_init = vhost_user_blk_server_class_init, - .interfaces = (InterfaceInfo[]) { - {TYPE_USER_CREATABLE}, - {} - }, +const BlockExportDriver blk_exp_vhost_user_blk = { + .type = BLOCK_EXPORT_TYPE_VHOST_USER_BLK, + .instance_size = sizeof(VuBlkExport), + .create = vu_blk_exp_create, + .delete = vu_blk_exp_delete, + .request_shutdown = vu_blk_exp_request_shutdown, }; - -static void vhost_user_blk_server_register_types(void) -{ - type_register_static(&vhost_user_blk_server_info); -} - -type_init(vhost_user_blk_server_register_types) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, Error **errp) { QEMUBH *bh; - QIONetListener *listener = qio_net_listener_new(); + QIONetListener *listener; + + if (socket_addr->type != SOCKET_ADDRESS_TYPE_UNIX && + socket_addr->type != SOCKET_ADDRESS_TYPE_FD) { + error_setg(errp, "Only socket address types 'unix' and 'fd' are supported"); + return false; + } + + listener = qio_net_listener_new(); if (qio_net_listener_open_sync(listener, socket_addr, 1, errp) < 0) { object_unref(OBJECT(listener)); diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -1 +1,2 @@ block_ss.add(files('export.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) diff --git a/block/meson.build b/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/meson.build +++ b/block/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -- 2.26.2 Headers used by other subsystems are located in include/. Also add the vhost-user-server and vhost-user-blk-server headers to MAINTAINERS. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-13-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 4 +++- {util => include/qemu}/vhost-user-server.h | 0 block/export/vhost-user-blk-server.c | 2 +- util/vhost-user-server.c | 2 +- 4 files changed, 5 insertions(+), 3 deletions(-) rename {util => include/qemu}/vhost-user-server.h (100%) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ Vhost-user block device backend server M: Coiby Xu <Coiby.Xu@gmail.com> S: Maintained F: block/export/vhost-user-blk-server.c -F: util/vhost-user-server.c +F: block/export/vhost-user-blk-server.h +F: include/qemu/vhost-user-server.h F: tests/qtest/libqos/vhost-user-blk.c +F: util/vhost-user-server.c Replication M: Wen Congyang <wencongyang2@huawei.com> diff --git a/util/vhost-user-server.h b/include/qemu/vhost-user-server.h similarity index 100% rename from util/vhost-user-server.h rename to include/qemu/vhost-user-server.h diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "contrib/libvhost-user/libvhost-user.h" #include "standard-headers/linux/virtio_blk.h" -#include "util/vhost-user-server.h" +#include "qemu/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "qemu/vhost-user-server.h" #include "block/aio-wait.h" -#include "vhost-user-server.h" /* * Theory of operation: -- 2.26.2 Don't compile contrib/libvhost-user/libvhost-user.c again. Instead build the static library once and then reuse it throughout QEMU. Also switch from CONFIG_LINUX to CONFIG_VHOST_USER, which is what the vhost-user tools (vhost-user-gpu, etc) do. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-14-stefanha@redhat.com [Added CONFIG_LINUX again because libvhost-user doesn't build on macOS. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/export.c | 8 ++++---- block/export/meson.build | 2 +- contrib/libvhost-user/meson.build | 1 + meson.build | 6 +++++- util/meson.build | 4 +++- 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" -#if CONFIG_LINUX -#include "block/export/vhost-user-blk-server.h" -#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" #include "qemu/id.h" +#ifdef CONFIG_VHOST_USER +#include "vhost-user-blk-server.h" +#endif static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, -#if CONFIG_LINUX +#ifdef CONFIG_VHOST_USER &blk_exp_vhost_user_blk, #endif }; diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files('export.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) +block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) diff --git a/contrib/libvhost-user/meson.build b/contrib/libvhost-user/meson.build index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/meson.build +++ b/contrib/libvhost-user/meson.build @@ -XXX,XX +XXX,XX @@ libvhost_user = static_library('vhost-user', files('libvhost-user.c', 'libvhost-user-glib.c'), build_by_default: false) +vhost_user = declare_dependency(link_with: libvhost_user) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ trace_events_subdirs += [ 'util', ] +vhost_user = not_found +if 'CONFIG_VHOST_USER' in config_host + subdir('contrib/libvhost-user') +endif + subdir('qapi') subdir('qobject') subdir('stubs') @@ -XXX,XX +XXX,XX @@ if have_tools install: true) if 'CONFIG_VHOST_USER' in config_host - subdir('contrib/libvhost-user') subdir('contrib/vhost-user-blk') subdir('contrib/vhost-user-gpu') subdir('contrib/vhost-user-input') diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('main-loop.c')) util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) - util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) + util_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: [ + files('vhost-user-server.c'), vhost_user + ]) util_ss.add(files('block-helpers.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) -- 2.26.2 Introduce libblkdev.fa to avoid recompiling blockdev_ss twice. Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200929125516.186715-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- meson.build | 12 ++++++++++-- storage-daemon/meson.build | 3 +-- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ blockdev_ss.add(files( # os-win32.c does not blockdev_ss.add(when: 'CONFIG_POSIX', if_true: files('os-posix.c')) softmmu_ss.add(when: 'CONFIG_WIN32', if_true: [files('os-win32.c')]) -softmmu_ss.add_all(blockdev_ss) common_ss.add(files('cpus-common.c')) @@ -XXX,XX +XXX,XX @@ block = declare_dependency(link_whole: [libblock], link_args: '@block.syms', dependencies: [crypto, io]) +blockdev_ss = blockdev_ss.apply(config_host, strict: false) +libblockdev = static_library('blockdev', blockdev_ss.sources() + genh, + dependencies: blockdev_ss.dependencies(), + name_suffix: 'fa', + build_by_default: false) + +blockdev = declare_dependency(link_whole: [libblockdev], + dependencies: [block]) + qmp_ss = qmp_ss.apply(config_host, strict: false) libqmp = static_library('qmp', qmp_ss.sources() + genh, dependencies: qmp_ss.dependencies(), @@ -XXX,XX +XXX,XX @@ foreach m : block_mods + softmmu_mods install_dir: config_host['qemu_moddir']) endforeach -softmmu_ss.add(authz, block, chardev, crypto, io, qmp) +softmmu_ss.add(authz, blockdev, chardev, crypto, io, qmp) common_ss.add(qom, qemuutil) common_ss.add_all(when: 'CONFIG_SOFTMMU', if_true: [softmmu_ss]) diff --git a/storage-daemon/meson.build b/storage-daemon/meson.build index XXXXXXX..XXXXXXX 100644 --- a/storage-daemon/meson.build +++ b/storage-daemon/meson.build @@ -XXX,XX +XXX,XX @@ qsd_ss = ss.source_set() qsd_ss.add(files('qemu-storage-daemon.c')) -qsd_ss.add(block, chardev, qmp, qom, qemuutil) -qsd_ss.add_all(blockdev_ss) +qsd_ss.add(blockdev, chardev, qmp, qom, qemuutil) subdir('qapi') -- 2.26.2 Block exports are used by softmmu, qemu-storage-daemon, and qemu-nbd. They are not used by other programs and are not otherwise needed in libblock. Undo the recent move of blockdev-nbd.c from blockdev_ss into block_ss. Since bdrv_close_all() (libblock) calls blk_exp_close_all() (libblockdev) a stub function is required.. Make qemu-nbd.c use signal handling utility functions instead of duplicating the code. This helps because os-posix.c is in libblockdev and it depends on a qemu_system_killed() symbol that qemu-nbd.c lacks. Once we use the signal handling utility functions we also end up providing the necessary symbol. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200929125516.186715-4-stefanha@redhat.com [Fixed s/ndb/nbd/ typo in commit description as suggested by Eric Blake --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-nbd.c | 21 ++++++++------------- stubs/blk-exp-close-all.c | 7 +++++++ block/export/meson.build | 4 ++-- meson.build | 4 ++-- nbd/meson.build | 2 ++ stubs/meson.build | 1 + 6 files changed, 22 insertions(+), 17 deletions(-) create mode 100644 stubs/blk-exp-close-all.c diff --git a/qemu-nbd.c b/qemu-nbd.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-nbd.c +++ b/qemu-nbd.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/cutils.h" #include "sysemu/block-backend.h" +#include "sysemu/runstate.h" /* for qemu_system_killed() prototype */ #include "block/block_int.h" #include "block/nbd.h" #include "qemu/main-loop.h" @@ -XXX,XX +XXX,XX @@ QEMU_COPYRIGHT "\n" } #ifdef CONFIG_POSIX -static void termsig_handler(int signum) +/* + * The client thread uses SIGTERM to interrupt the server. A signal + * handler ensures that "qemu-nbd -v -c" exits with a nice status code. + */ +void qemu_system_killed(int signum, pid_t pid) { qatomic_cmpxchg(&state, RUNNING, TERMINATE); qemu_notify_event(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) BlockExportOptions *export_opts; #ifdef CONFIG_POSIX - /* - * Exit gracefully on various signals, which includes SIGTERM used - * by 'qemu-nbd -v -c'. - */ - struct sigaction sa_sigterm; - memset(&sa_sigterm, 0, sizeof(sa_sigterm)); - sa_sigterm.sa_handler = termsig_handler; - sigaction(SIGTERM, &sa_sigterm, NULL); - sigaction(SIGINT, &sa_sigterm, NULL); - sigaction(SIGHUP, &sa_sigterm, NULL); - - signal(SIGPIPE, SIG_IGN); + os_setup_early_signal_handling(); + os_setup_signal_handling(); #endif socket_init(); diff --git a/stubs/blk-exp-close-all.c b/stubs/blk-exp-close-all.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/stubs/blk-exp-close-all.c @@ -XXX,XX +XXX,XX @@ +#include "qemu/osdep.h" +#include "block/export.h" + +/* Only used in programs that support block exports (libblockdev.fa) */ +void blk_exp_close_all(void) +{ +} diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ -block_ss.add(files('export.c')) -block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) +blockdev_ss.add(files('export.c')) +blockdev_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ subdir('dump') block_ss.add(files( 'block.c', - 'blockdev-nbd.c', 'blockjob.c', 'job.c', 'qemu-io-cmds.c', @@ -XXX,XX +XXX,XX @@ subdir('block') blockdev_ss.add(files( 'blockdev.c', + 'blockdev-nbd.c', 'iothread.c', 'job-qmp.c', )) @@ -XXX,XX +XXX,XX @@ if have_tools qemu_io = executable('qemu-io', files('qemu-io.c'), dependencies: [block, qemuutil], install: true) qemu_nbd = executable('qemu-nbd', files('qemu-nbd.c'), - dependencies: [block, qemuutil], install: true) + dependencies: [blockdev, qemuutil], install: true) subdir('storage-daemon') subdir('contrib/rdmacm-mux') diff --git a/nbd/meson.build b/nbd/meson.build index XXXXXXX..XXXXXXX 100644 --- a/nbd/meson.build +++ b/nbd/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files( 'client.c', 'common.c', +)) +blockdev_ss.add(files( 'server.c', )) diff --git a/stubs/meson.build b/stubs/meson.build index XXXXXXX..XXXXXXX 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -XXX,XX +XXX,XX @@ stub_ss.add(files('arch_type.c')) stub_ss.add(files('bdrv-next-monitor-owned.c')) stub_ss.add(files('blk-commit-all.c')) +stub_ss.add(files('blk-exp-close-all.c')) stub_ss.add(files('blockdev-close-all-bdrv-states.c')) stub_ss.add(files('change-state-handler.c')) stub_ss.add(files('cmos.c')) -- 2.26.2 Make it possible to specify the iothread where the export will run. By default the block node can be moved to other AioContexts later and the export will follow. The fixed-iothread option forces strict behavior that prevents changing AioContext while the export is active. See the QAPI docs for details. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200929125516.186715-5-stefanha@redhat.com [Fix stray '#' character in block-export.json and add missing "(since: 5.2)" as suggested by Eric Blake. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 11 ++++++++++ block/export/export.c | 31 +++++++++++++++++++++++++++- block/export/vhost-user-blk-server.c | 5 ++++- nbd/server.c | 2 -- 4 files changed, 45 insertions(+), 4 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ # export before completion is signalled. (since: 5.2; # default: false) # +# @iothread: The name of the iothread object where the export will run. The +# default is to use the thread currently associated with the +# block node. (since: 5.2) +# +# @fixed-iothread: True prevents the block node from being moved to another +# thread while the export is active. If true and @iothread is +# given, export creation fails if the block node cannot be +# moved to the iothread. The default is false. (since: 5.2) +# # Since: 4.2 ## { 'union': 'BlockExportOptions', 'base': { 'type': 'BlockExportType', 'id': 'str', + '*fixed-iothread': 'bool', + '*iothread': 'str', 'node-name': 'str', '*writable': 'bool', '*writethrough': 'bool' }, diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "sysemu/block-backend.h" +#include "sysemu/iothread.h" #include "block/export.h" #include "block/nbd.h" #include "qapi/error.h" @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_find_driver(BlockExportType type) BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) { + bool fixed_iothread = export->has_fixed_iothread && export->fixed_iothread; const BlockExportDriver *drv; BlockExport *exp = NULL; BlockDriverState *bs; - BlockBackend *blk; + BlockBackend *blk = NULL; AioContext *ctx; uint64_t perm; int ret; @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) ctx = bdrv_get_aio_context(bs); aio_context_acquire(ctx); + if (export->has_iothread) { + IOThread *iothread; + AioContext *new_ctx; + + iothread = iothread_by_id(export->iothread); + if (!iothread) { + error_setg(errp, "iothread \"%s\" not found", export->iothread); + goto fail; + } + + new_ctx = iothread_get_aio_context(iothread); + + ret = bdrv_try_set_aio_context(bs, new_ctx, errp); + if (ret == 0) { + aio_context_release(ctx); + aio_context_acquire(new_ctx); + ctx = new_ctx; + } else if (fixed_iothread) { + goto fail; + } + } + /* * Block exports are used for non-shared storage migration. Make sure * that BDRV_O_INACTIVE is cleared and the image is ready for write @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) } blk = blk_new(ctx, perm, BLK_PERM_ALL); + + if (!fixed_iothread) { + blk_set_allow_aio_context_change(blk, true); + } + ret = blk_insert_bs(blk, bs, errp); if (ret < 0) { goto fail; diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_blk_iface = { static void blk_aio_attached(AioContext *ctx, void *opaque) { VuBlkExport *vexp = opaque; + + vexp->export.ctx = ctx; vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); + vexp->export.ctx = NULL; } static void @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, logical_block_size); - blk_set_allow_aio_context_change(exp->blk, true); blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); diff --git a/nbd/server.c b/nbd/server.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -XXX,XX +XXX,XX @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, return ret; } - blk_set_allow_aio_context_change(blk, true); - QTAILQ_INIT(&exp->clients); exp->name = g_strdup(arg->name); exp->description = g_strdup(arg->description); -- 2.26.2 Allow the number of queues to be configured using --export vhost-user-blk,num-queues=N. This setting should match the QEMU --device vhost-user-blk-pci,num-queues=N setting but QEMU vhost-user-blk.c lowers its own value if the vhost-user-blk backend offers fewer queues than QEMU. The vhost-user-blk-server.c code is already capable of multi-queue. All virtqueue processing runs in the same AioContext. No new locking is needed. Add the num-queues=N option and set the VIRTIO_BLK_F_MQ feature bit. Note that the feature bit only announces the presence of the num_queues configuration space field. It does not promise that there is more than 1 virtqueue, so we can set it unconditionally. I tested multi-queue by running a random read fio test with numjobs=4 on an -smp 4 guest. After the benchmark finished the guest /proc/interrupts file showed activity on all 4 virtio-blk MSI-X. The /sys/block/vda/mq/ directory shows that Linux blk-mq has 4 queues configured. An automated test is included in the next commit. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20201001144604.559733-2-stefanha@redhat.com [Fixed accidental tab characters as suggested by Markus Armbruster --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 10 +++++++--- block/export/vhost-user-blk-server.c | 24 ++++++++++++++++++------ 2 files changed, 25 insertions(+), 9 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ # SocketAddress types are supported. Passed fds must be UNIX domain # sockets. # @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. +# @num-queues: Number of request virtqueues. Must be greater than 0. Defaults +# to 1. # # Since: 5.2 ## { 'struct': 'BlockExportOptionsVhostUserBlk', - 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } + 'data': { 'addr': 'SocketAddress', + '*logical-block-size': 'size', + '*num-queues': 'uint16'} } ## # @NbdServerAddOptions: @@ -XXX,XX +XXX,XX @@ { 'union': 'BlockExportOptions', 'base': { 'type': 'BlockExportType', 'id': 'str', - '*fixed-iothread': 'bool', - '*iothread': 'str', + '*fixed-iothread': 'bool', + '*iothread': 'str', 'node-name': 'str', '*writable': 'bool', '*writethrough': 'bool' }, diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #include "util/block-helpers.h" enum { - VHOST_USER_BLK_MAX_QUEUES = 1, + VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1, }; struct virtio_blk_inhdr { unsigned char status; @@ -XXX,XX +XXX,XX @@ static uint64_t vu_blk_get_features(VuDev *dev) 1ull << VIRTIO_BLK_F_DISCARD | 1ull << VIRTIO_BLK_F_WRITE_ZEROES | 1ull << VIRTIO_BLK_F_CONFIG_WCE | + 1ull << VIRTIO_BLK_F_MQ | 1ull << VIRTIO_F_VERSION_1 | 1ull << VIRTIO_RING_F_INDIRECT_DESC | 1ull << VIRTIO_RING_F_EVENT_IDX | @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) static void vu_blk_initialize_config(BlockDriverState *bs, - struct virtio_blk_config *config, uint32_t blk_size) + struct virtio_blk_config *config, + uint32_t blk_size, + uint16_t num_queues) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; config->blk_size = blk_size; @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, config->seg_max = 128 - 2; config->min_io_size = 1; config->opt_io_size = 1; - config->num_queues = VHOST_USER_BLK_MAX_QUEUES; + config->num_queues = num_queues; config->max_discard_sectors = 32768; config->max_discard_seg = 1; config->discard_sector_alignment = config->blk_size >> 9; @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; Error *local_err = NULL; uint64_t logical_block_size; + uint16_t num_queues = VHOST_USER_BLK_NUM_QUEUES_DEFAULT; vexp->writable = opts->writable; vexp->blkcfg.wce = 0; @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, } vexp->blk_size = logical_block_size; blk_set_guest_block_size(exp->blk, logical_block_size); + + if (vu_opts->has_num_queues) { + num_queues = vu_opts->num_queues; + } + if (num_queues == 0) { + error_setg(errp, "num-queues must be greater than 0"); + return -EINVAL; + } + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, - logical_block_size); + logical_block_size, num_queues); blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, - errp)) { + num_queues, &vu_blk_iface, errp)) { blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); return -EADDRNOTAVAIL; -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bdrv_co_block_status_above has several design problems with handling short backing files: 1. With want_zeros=true, it may return ret with BDRV_BLOCK_ZERO but without BDRV_BLOCK_ALLOCATED flag, when actually short backing file which produces these after-EOF zeros is inside requested backing sequence. 2. With want_zero=false, it may return pnum=0 prior to actual EOF, because of EOF of short backing file. Fix these things, making logic about short backing files clearer. With fixed bdrv_block_status_above we also have to improve is_zero in qcow2 code, otherwise iotest 154 will fail, because with this patch we stop to merge zeros of different types (produced by fully unallocated in the whole backing chain regions vs produced by short backing files). Note also, that this patch leaves for another day the general problem around block-status: misuse of BDRV_BLOCK_ALLOCATED as is-fs-allocated vs go-to-backing. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200924194003.22080-2-vsementsov@virtuozzo.com [Fix s/comes/come/ as suggested by Eric Blake --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 68 ++++++++++++++++++++++++++++++++++++++++----------- block/qcow2.c | 16 ++++++++++-- 2 files changed, 68 insertions(+), 16 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, int64_t *map, BlockDriverState **file) { + int ret; BlockDriverState *p; - int ret = 0; - bool first = true; + int64_t eof = 0; assert(bs != base); - for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) { + + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { + return ret; + } + + if (ret & BDRV_BLOCK_EOF) { + eof = offset + *pnum; + } + + assert(*pnum <= bytes); + bytes = *pnum; + + for (p = bdrv_filter_or_cow_bs(bs); p != base; + p = bdrv_filter_or_cow_bs(p)) + { ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, file); if (ret < 0) { - break; + return ret; } - if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { + if (*pnum == 0) { /* - * Reading beyond the end of the file continues to read - * zeroes, but we can only widen the result to the - * unallocated length we learned from an earlier - * iteration. + * The top layer deferred to this layer, and because this layer is + * short, any zeroes that we synthesize beyond EOF behave as if they + * were allocated at this layer. + * + * We don't include BDRV_BLOCK_EOF into ret, as upper layer may be + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see + * below. */ + assert(ret & BDRV_BLOCK_EOF); *pnum = bytes; + if (file) { + *file = p; + } + ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED; + break; } - if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { + if (ret & BDRV_BLOCK_ALLOCATED) { + /* + * We've found the node and the status, we must break. + * + * Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see + * below. + */ + ret &= ~BDRV_BLOCK_EOF; break; } - /* [offset, pnum] unallocated on this layer, which could be only - * the first part of [offset, bytes]. */ - bytes = MIN(bytes, *pnum); - first = false; + + /* + * OK, [offset, offset + *pnum) region is unallocated on this layer, + * let's continue the diving. + */ + assert(*pnum <= bytes); + bytes = *pnum; + } + + if (offset + *pnum == eof) { + ret |= BDRV_BLOCK_EOF; } + return ret; } diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) if (!bytes) { return true; } - res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; + + /* + * bdrv_block_status_above doesn't merge different types of zeros, for + * example, zeros which come from the region which is unallocated in + * the whole backing chain, and zeros which come because of a short + * backing file. So, we need a loop. + */ + do { + res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); + offset += nr; + bytes -= nr; + } while (res >= 0 && (res & BDRV_BLOCK_ZERO) && nr && bytes); + + return res >= 0 && (res & BDRV_BLOCK_ZERO) && bytes == 0; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> In order to reuse bdrv_common_block_status_above in bdrv_is_allocated_above, let's support include_base parameter. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200924194003.22080-3-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/coroutines.h | 2 ++ block/io.c | 21 ++++++++++++++------- 2 files changed, 16 insertions(+), 7 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ bdrv_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, int coroutine_fn bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, int generated_co_wrapper bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ early_out: int coroutine_fn bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t eof = 0; - assert(bs != base); + assert(include_base || bs != base); + assert(!include_base || base); /* Can't include NULL base */ ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); - if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; } @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, assert(*pnum <= bytes); bytes = *pnum; - for (p = bdrv_filter_or_cow_bs(bs); p != base; + for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; p = bdrv_filter_or_cow_bs(p)) { ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, break; } + if (p == base) { + assert(include_base); + break; + } + /* * OK, [offset, offset + *pnum) region is unallocated on this layer, * let's continue the diving. @@ -XXX,XX +XXX,XX @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file) { - return bdrv_common_block_status_above(bs, base, true, offset, bytes, + return bdrv_common_block_status_above(bs, base, false, true, offset, bytes, pnum, map, file); } @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int ret; int64_t dummy; - ret = bdrv_common_block_status_above(bs, bdrv_filter_or_cow_bs(bs), false, - offset, bytes, pnum ? pnum : &dummy, - NULL, NULL); + ret = bdrv_common_block_status_above(bs, bs, true, false, offset, + bytes, pnum ? pnum : &dummy, NULL, + NULL); if (ret < 0) { return ret; } -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to reuse bdrv_common_block_status_above in bdrv_is_allocated_above. bdrv_is_allocated_above may be called with include_base == false and still bs == base (for ex. from img_rebase()). So, support this corner case. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-4-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t eof = 0; - assert(include_base || bs != base); assert(!include_base || base); /* Can't include NULL base */ + if (!include_base && bs == base) { + *pnum = bytes; + return 0; + } + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bdrv_is_allocated_above wrongly handles short backing files: it reports after-EOF space as UNALLOCATED which is wrong, as on read the data is generated on the level of short backing file (if all overlays have unallocated areas at that place). Reusing bdrv_common_block_status_above fixes the issue and unifies code path. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-5-vsementsov@virtuozzo.com [Fix s/has/have/ as suggested by Eric Blake. Fix s/area/areas/. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 43 +++++-------------------------------------- 1 file changed, 5 insertions(+), 38 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, * at 'offset + *pnum' may return the same allocation status (in other * words, the result is not necessarily the maximum possible range); * but 'pnum' will only be 0 when end of file is reached. - * */ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, bool include_base, int64_t offset, int64_t bytes, int64_t *pnum) { - BlockDriverState *intermediate; - int ret; - int64_t n = bytes; - - assert(base || !include_base); - - intermediate = top; - while (include_base || intermediate != base) { - int64_t pnum_inter; - int64_t size_inter; - - assert(intermediate); - ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter); - if (ret < 0) { - return ret; - } - if (ret) { - *pnum = pnum_inter; - return 1; - } - - size_inter = bdrv_getlength(intermediate); - if (size_inter < 0) { - return size_inter; - } - if (n > pnum_inter && - (intermediate == top || offset + pnum_inter < size_inter)) { - n = pnum_inter; - } - - if (intermediate == base) { - break; - } - - intermediate = bdrv_filter_or_cow_bs(intermediate); + int ret = bdrv_common_block_status_above(top, base, include_base, false, + offset, bytes, pnum, NULL, NULL); + if (ret < 0) { + return ret; } - *pnum = n; - return 0; + return !!(ret & BDRV_BLOCK_ALLOCATED); } int coroutine_fn -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> These cases are fixed by previous patches around block_status and is_allocated. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-6-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qemu-iotests/274 | 20 +++++++++++ tests/qemu-iotests/274.out | 68 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/274 +++ b/tests/qemu-iotests/274 @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base') as base, \ iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + iotests.log('=== Testing qemu-img commit (top -> base) ===') + + create_chain() + iotests.qemu_img_log('commit', '-b', base, top) + iotests.img_info_log(base) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) + + iotests.log('=== Testing QMP active commit (top -> base) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('block-commit', device='top', base_node='base', + job_id='job0', auto_dismiss=False) + vm.run_job('job0', wait=5) + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) iotests.log('== Resize tests ==') diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 0 read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +=== Testing qemu-img commit (top -> base) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image committed. + +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +Format specific information: + compat: 1.1 + compression type: zlib + lazy refcounts: false + refcount bits: 16 + corrupt: false + extended l2: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing QMP active commit (top -> base) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "base", "device": "top", "job-id": "job0"}} +{"return": {}} +{"execute": "job-complete", "arguments": {"id": "job0"}} +{"return": {}} +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"execute": "job-dismiss", "arguments": {"id": "job0"}} +{"return": {}} +image: TEST_IMG +file format: IMGFMT +virtual size: 1 MiB (1048576 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +backing file format: IMGFMT +Format specific information: + compat: 1.1 + compression type: zlib + lazy refcounts: false + refcount bits: 16 + corrupt: false + extended l2: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + == Resize tests == === preallocation=off === Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=6442450944 lazy_refcounts=off refcount_bits=16 -- 2.26.2