Commit Graph

1269 Commits

Author SHA1 Message Date
Michal Privoznik
e8c2c8bd07 qemu_command: Prefer '-overcommit mem-lock' over -realtime mlock'
The latter is deprecated and will be removed soon. The advised
replacement is '-overcommit mem-lock=on|off'.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-12 14:13:45 +02:00
Michal Privoznik
a08c4b3741 qemu: Always assume QEMU_CAPS_REALTIME_MLOCK
The '-realtime mlock' cmd line argument was introduced in QEMU
commit v1.5.0-rc0~190 which matches minimal QEMU version we
require. Therefore, the capability will always be present.

Apparently, nearly none of our xml2argv test cases had the
capability hence slightly bigger change under qemuxml2argvdata/.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-12 13:39:42 +02:00
Ján Tomko
4dadcaa98e qemuxml2argvtest: remove old mlock tests
Now that we test with real QEMU data, remove the tests which enumerated
the capabilities.

Signed-off-by: Ján Tomko <jtomko@redhat.com>
2019-04-12 13:28:29 +02:00
Ján Tomko
02c84f0302 qemuxml2argvtest: add mlock tests for latest QEMU
Test the memory locking command line with different QEMU versions
to prepare for changing it for latest QEMU.

Signed-off-by: Ján Tomko <jtomko@redhat.com>
2019-04-12 13:28:29 +02:00
Ján Tomko
18161cf7df qemuxml2argvtest: add mlock tests for QEMU 3.0.0
Test the memory locking command line with different QEMU versions
to prepare for changing it for latest QEMU.

Signed-off-by: Ján Tomko <jtomko@redhat.com>
2019-04-12 13:28:29 +02:00
Andrea Bolognani
e602e86881 tests: Refresh capabilities for QEMU 4.0.0 on RISC-V
There are a few differences, but the one we're interested in is
that PCIe Root Ports are finally available: as a result of this,
our riscv64-virt-headless guest will switch from virtio-mmio to
virtio-pci.

Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Reviewed-by: Cole Robinson <crobinso@redhat.com>
2019-04-04 09:52:23 +02:00
Michal Privoznik
6864d8f740 qemuBuildMemoryBackendProps: Get pagesize early
https://bugzilla.redhat.com/show_bug.cgi?id=1693066

Up until memfd introduction (in 24b74d187c) we did not need to
know @pagesize because qemuGetDomainHupageMemPath() could deal
with it being zero (value of zero means use the default hugetlbfs
mount). But since for memfd we are not passing a path to
hugetlbfs mount rather the page size value we need to know its
value upfront.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-03 16:37:19 +02:00
Michal Privoznik
59a22be864 qemuxml2xmltest: Add memfd tests
Somehow, these were not tested. Use symlinks to point expected
output back to the input. This way we can also fix some
discrepancies in the input XMLs.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-03 16:37:19 +02:00
Michal Privoznik
7086c835b6 qemuxml2argvdata: Drop useless spaces at the beginning of lines
There are three test XMLs that have useless spaces at the
beginning of each line. I intend to add these to qemuxml2xmltest
and make xmlout a symlink to the original XML. In order to do
that the XMLs must look better than they do now.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-03 16:37:19 +02:00
Peter Krempa
22b83a54f5 conf: Add 'index' attribute for <disk><mirror><source>
Similarly to the disk source we need to keep the disk index (which is in
the qemu driver used for identification of the source for block jobs)
for the <mirror> element so that when it's replaced as a disk source
after pivoting all the allocated data is present.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-03 11:58:09 +02:00
Peter Krempa
4e797f1af9 conf: Parse and format 'backingStore' for disk <mirror>
When the block copy operation is started with a reused external file in
incremental mode libvirt will need to open and insert the backing chain
for that file into qemu (in -blockdev mode). This means that we'll need
to track the backing chain and metadata such as node names for the full
chain of <mirror>.

This patch invokes the full backing chain formatter and parser for
<mirror> so that the chain can be kept with <mirror>.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-03 11:58:09 +02:00
Peter Krempa
da9f3cd84b conf: Format seclabels for <backingStore>
We parse the seclabels and use them internally so omitting them when
formatting would be misleading. Additionally our schema actually allows
them.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
2019-04-03 11:58:09 +02:00
Andrea Bolognani
9d3aa7c6e9 tests: Add s390x-ccw-graphics test case
We have tests for simple guests with graphics for basically
all other architectures, so it makes sense to include s390x
too.

The input file was generated by running

  $ virt-install \
    --name guest --os-variant fedora29 \
    --vcpus 4 --memory 4096 --disk size=5 \
    --graphics vnc \
    --print-xml

followed by minor tweaks, using a version of virt-manager
that includes commit 7b9de27a990f.

Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Acked-by: Michal Privoznik <mprivozn@redhat.com>
2019-03-22 16:30:59 +01:00
Andrea Bolognani
9f33f4772b tests: Update aarch64-virt-graphics for virtio-blk
As of commit db6c7070e25a, virt-manager will default to using
virtio-blk rather than virtio-scsi for aarch64/virt guests,
bringing them in line with other architectures. Update our test
case to reflect this change.

Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Acked-by: Michal Privoznik <mprivozn@redhat.com>
2019-03-22 16:30:59 +01:00
Erik Skultety
75a9169881 qemu: command: Override HOME variable for system QEMU
By default, qemu user's home dir points to '/' which shouldn't be used
at all. We therefore pass the HOME variable from the current variable
iff not running as SUID, which means that for systemd we never set it.
This patch makes sure, that for system QEMU this is always set to
libDir/<driver>, session mode is left untouched.

Signed-off-by: Erik Skultety <eskultet@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
2019-03-15 16:41:26 +01:00
Erik Skultety
7e73137495 qemu: command: Enforce setting XDG variables for system QEMU
For session mode, only XDG_CACHE_HOME is set, because we want to remain
integrating with services in user session, but for system mode, this
would have become reading/writing to '/' which carries the obvious issue
with permissions (also, '/' is the wrong location in 99.9% cases anyway).

Signed-off-by: Erik Skultety <eskultet@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
2019-03-15 16:41:26 +01:00
Michal Privoznik
68ade25372 qemu: Enable firmware autoselection
https://bugzilla.redhat.com/show_bug.cgi?id=1564270

Now that everything is prepared for qemu driver we can enable
parser feature to allow users define such domains.

At the same time, introduce bunch of tests to test the feature.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
2019-03-12 16:09:55 +01:00
Andrea Bolognani
186bb479d0 qemu: Allow creating ppc64 guests with graphics and no USB mouse
The existing behavior for ppc64 guests is to always add a USB
keyboard and mouse combo if graphics are present; unfortunately,
this means any attempt to use a USB tablet will cause both pointing
devices to show up in the guest, which in turn will result in poor
user experience.

We can't just stop adding the USB mouse or start adding a USB tablet
instead, because existing applications and users might rely on the
current behavior; however, we can avoid adding the USB mouse if a USB
tablet is already present, thus allowing users and applications to
create guests that contain a single pointing device.

https://bugzilla.redhat.com/show_bug.cgi?id=1683681

Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Reviewed-by: Cole Robinson <crobinso@redhat.com>
2019-03-11 09:59:34 +01:00
Andrea Bolognani
4d7ea75e1e tests: Add simple guests with graphics to qemuxml2argv
These are similar to the existing simple headless guests, but
also include a graphical output and some input devices.

Input files were generated by running

  $ virt-install \
    --name guest --os-variant fedora29 \
    --vcpus 4 --memory 4096 --disk size=5 \
    --graphics vnc \
    --print-xml

followed by minor tweaks.

Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Reviewed-by: Cole Robinson <crobinso@redhat.com>
2019-03-11 09:59:11 +01:00
Andrea Bolognani
ff3f22e0ec qemu: Improve validation for virtio input devices
While the parser and schema have to accept all possible models,
virtio-(non-)transitional models are only applicable to
type=passthrough and should be otherwise rejected.

Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Reviewed-by: Cole Robinson <crobinso@redhat.com>
2019-03-11 09:53:40 +01:00
Cole Robinson
448a094717 qemu: Support scsi controller model=virtio-{non-}transitional
Add <controller type='scsi' model handling for virtio transitional
devices. Ex:

  <controller type='scsi' model='virtio-transitional'/>

* "virtio-transitional" maps to qemu "virtio-scsi-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-scsi-non-transitional"

The naming here doesn't match the pre-existing model=virtio-scsi.
The prescence of '-scsi' there seems kind of redundant as we have
type='scsi' already, so I decided to follow the pattern of other
patches and use virtio-transitional etc.

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
47f94f4591 qemu: Support virtio-serial controller model=virtio-{non-}transitional
Add controller type='virtio-serial' model handling for virtio
transitional devices. Ex:

  <controller type='virtio-serial' model='virtio-transitional'/>

* "virtio-transitional" maps to qemu "virtio-serial-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-serial-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
90fd9bd989 qemu: Support input model=virtio-{non-}transitional
Add <input> model handling for virtio transitional devices. Ex:

  <input type='passthrough' bus='virtio' model='virtio-transitional'>
    ...
  </input>

* "virtio-transitional" maps to qemu "virtio-input-host-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-input-host-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
2593a1bd1a conf: Add <input model='virtio-{non-}transitional'/>
<input> devices lack the model= attribute which is used by
most other device types. To eventually support
virtio-input-host-pci-{non-}traditional in qemu, let's add
a standard model= attribute. This just adds the domain_conf
wiring

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
6e64899284 qemu: Support vsock model=virtio-{non-}transitional
Add <vsock> model handling for virtio transitional devices. Ex:

  <vsock model='virtio-transitional'>
    ...
  </vsock>

* "virtio-transitional" maps to qemu "vhost-vsock-pci-transitional"
* "virtio-non-transitional" maps to qemu "vhost-vsock-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
0f5958f5c5 qemu: Support memballoon model=virtio-{non-}transitional
Add new <memballoon> model values for virtio transitional devices. Ex:

  <memballoon model='virtio-transitional'/>

* "virtio-transitional" maps to qemu "virtio-balloon-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-balloon-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
62eef965ba qemu: Support filesystem model=virtio-{non-}transitional
Add <filesystem> model handling for virtio transitional devices. Ex:

  <filesystem type='mount' model='virtio-transitional'>
    ...
  </filesystem

* "virtio-transitional" maps to qemu "virtio-9p-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-9p-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
947448e212 conf: Add <filesystem model='virtio-{non-}transitional'/>
<filesystem> devices lack the model= attribute which is used by
most other device types. To eventually support
virtio-9p-pci-{non-}traditional in qemu, let's add a standard
model= attribute. The accepted values are:

- virtio
- virtio-transitional
- virtio-non-transitional

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
e063707556 qemu: Support rng model=virtio-{non-}transitional
Add new <rng> model values for virtio transitional devices. Ex:

  <rng model='virtio-transitional'>
    ...
  </rng>

* "virtio-transitional" maps to qemu "virtio-rng-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-rng-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:41 -05:00
Cole Robinson
37f75d56da qemu: Support hostdev model=virtio-{non-}transitional
Add <hostdev> protocol=vhost model handling for virtio transitional
devices. Ex:

  <hostdev mode='subsystem' type='scsi_host' model='virtio-transitional'>
    <source protocol='vhost' wwpn=X/>
  </hostdev>

* "virtio-transitional" maps to qemu "vhost-scsi-pci-transitional"
* "virtio-non-transitional" maps to qemu "vhost-scsi-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:40 -05:00
Cole Robinson
ef41ff4219 conf: Add <hostdev model='virtio-{non-}transitional'/>
qemu vhost-scsi devices map to XML roughly like:

    <hostdev mode='subsystem' type='scsi_host'>
      <source protocol='vhost' wwpn=X/>
    </hostdev>

To support vhost-scsi-pci-{non-}traditional in qemu, we
need to to extend the SCSI Host hostdev XML to handle
model= value. This matches the XML model= format used
for mediated devices. This is just the domain_conf bits
and some XML test cases.

Use of virtio-X naming here does not match the hostdev
protocol=vhost nor does it match the qemu vhost-X device
naming, however it's more consistent with all other
model= names in this area, and also matches the
inconsistency of <vsock> devices which use model=virtio
but map to vhost-vsock on the qemu commandline

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:40 -05:00
Cole Robinson
4d964373b5 qemu: Support interface model=virtio-{non-}transitional
Add new <interface> model handling for virtio transitional devices. Ex:

<interface>
  <model type='virtio-transitional'/>
</interface>

* "virtio-transitional" maps to qemu "virtio-net-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-net-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:40 -05:00
Cole Robinson
239b535d99 qemu: Support disk model=virtio-{non-}transitional
Add new <disk> model values for virtio transitional devices. When
combined with bus='virtio':

* "virtio-transitional" maps to qemu "virtio-blk-pci-transitional"
* "virtio-non-transitional" maps to qemu "virtio-blk-pci-non-transitional"

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:40 -05:00
Cole Robinson
25d05051b3 conf: Add <disk model='virtio-{non-}transitional'/>
<disk> devices lack the model= attribute which is used by
most other device types. bus= mostly acts as one, but it
serves other purposes too like determing what target=
prefix to use, and for matching against controller type=
values.

Extending bus= to handle additional virtio transitional
devices will complicate apps lives, and it isn't a clean
mapping anyways. So let's bite the bullet and add a new
<disk model=X/> attribute, and wire up common handling
for virtio and virtio-{non-}transitional

Reviewed-by: Andrea Bolognani <abologna@redhat.com>
Signed-off-by: Cole Robinson <crobinso@redhat.com>
2019-03-04 11:08:40 -05:00
Michal Privoznik
18b8f67745 qemuL: Drop "user-" prefix for guestfwd netdev
Introduced by d86c876a66.

There is no real need to have "user-" prefix for chardev.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: John Ferlan <jferlan@redhat.com>
2019-02-14 09:18:31 +01:00
Peter Krempa
ea34af1f35 qemu: caps: Always assume QEMU_CAPS_SEAMLESS_MIGRATION
The event was added by qemu commit 2fdd16e239c2a2 released in v1.3.0.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 10:11:20 +01:00
Peter Krempa
a1dce96236 qemu: Use the 'device_id' property of SCSI disks to avoid regressing
QEMU accidentally exposed the id of -drive (or same value as disk
serial, if provided) in one of the identifiers visible from the guest.

To avoid regression in case when -blockdev will be used we need to
always specify it ourselves.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 10:11:12 +01:00
Peter Krempa
9222b402e5 tests: qemuxml2argv: Add a 'serial' value for a SCSI disk
Upcoming addition of a new field will need to make sure that SCSI disk
serial is tested as well. Add a case to one of the existing tests.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:48:33 +01:00
Peter Krempa
1328a830ce qemu: command: Drop formatting of 'media=cdrom' from -drive
For SCSI, IDE, and AHCI cdroms the appropriate device types which select
the correct media are used. In qemu there's one other code path that
looks at -drive media=cdrom in the XEN pv code. Thankfully we don't
support it with qemu (see qemuBuildDiskDeviceStr). All other devices
ignore it as the comment states, thus we can drop that code.

The test fallout is expectedly only in the test added for uncommon cdrom
types.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:48:33 +01:00
Peter Krempa
ea13c12940 tests: qemuxml2argv: Add CDROM disks for all untested buses
Add full and empty cdroms on 'usb' and 'sd' bus to have test
coverage. Note that this does not guarantee that qemu will accept them.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:48:11 +01:00
Peter Krempa
5d884f3d3c qemu: Forbid cdroms on virtio bus
Attempting to create an empty virtio-blk drive results into:
-device virtio-blk-pci,scsi=off,bus=pci.0,addr=0xc,drive=drive-virtio-disk1,id=virtio-disk1: Device needs media, but drive is empty

Attempting to eject media from virtio-blk based drive results into:
error: internal error: unable to execute QEMU command 'eject': Device 'drive-virtio-disk0' is not removable

Forbid configurations where users would attempt to use cdroms in virtio
bus.

Fix few wrong examples which are not really relevant to the tested code.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:41:40 +01:00
Peter Krempa
1dcba456fa qemu: caps: Always assume presence of 'ide-hd' and 'ide-cd' devices
The split of ide-disk into the two separate devices was introduced by
qemu commit 1f56e32a7f4b3 released in qemu v0.15.

Note that when compared to the previous commit which made sure that no
disk related tests were touched, in this case it's not as careful.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:34:17 +01:00
Peter Krempa
4bf49bc566 qemu: caps: Always assume presence of 'scsi-hd' and 'scsi-cd' device
The split of scsi-disk into the two separate devices was introduced by
qemu commit b443ae67 released in qemu v0.15.

All changes to test files are not really related to disk testing thanks
to previous refactors.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:34:17 +01:00
Peter Krempa
12116c018d tests: qemuxml2argv: Remove 'disk-virtio-scsi-ccw' test
It's a subset of 'iothreads-virtio-scsi-ccw'.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:34:17 +01:00
Peter Krempa
76709a76ba tests: qemuxml2argv: Modernize virtio-scsi iothread tests
Use DO_TEST_CAPS_LATEST to obtain modern results.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:34:04 +01:00
Peter Krempa
253ddf5a75 tests: qemuxml2argv: Use 1.5.3 version for the oldest case of 'disk-cache'
Rather than testing random set of flags add a case also for the oldest
supported qemu.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:33:10 +01:00
Peter Krempa
61900c4cda tests: qemu: Merge 'disk-scsi-vscsi' test into 'disk-scsi'
As we support multiple scsi controllers there's no need to have a
special test for this controller.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:32:40 +01:00
Peter Krempa
ee39011a09 tests: qemu: Merge 'disk-scsi-mptsas1068' test into 'disk-scsi'
As we support multiple scsi controllers there's no need to have a
special test for this controller.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:32:40 +01:00
Peter Krempa
a11e333779 tests: qemu: Merge 'disk-scsi-megasas' test into 'disk-scsi'
As we support multiple scsi controllers there's no need to have a
special test for this controller.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:32:40 +01:00
Peter Krempa
7523e60a94 tests: qemuxml2argv: Modernize 'disk-scsi' test
Use DO_TEST_CAPS_LATEST rather than a predetermined set of caps.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
2019-02-08 08:32:40 +01:00