From db64acfbda59ad22b671580fda13968c60bb8c1a Mon Sep 17 00:00:00 2001 From: Laine Stump Date: Thu, 11 Feb 2021 00:58:29 -0500 Subject: [PATCH] conf: parse/format element in plain The element in allows pairing two interfaces together as a simple "failover bond" network device in a guest. One of the devices is the "transient" interface - it will be preferred for all network traffic when it is present, but may be removed when necessary, in particular during migration, when traffic will instead go through the other interface of the pair - the "persistent" interface. As it happens, in the QEMU implementation of this teaming pair (called "virtio failover" in QEMU) the transient interface is always a host network device assigned to the guest using VFIO (aka "hostdev"); the persistent interface is always an emulated virtio NIC. When support was initially added for , it was written to require that the transient/hostdev device be defined using ; this was done because the virtio failover implementation in QEMU and the virtio guest driver demands that the two interfaces in the pair have matching MAC addresses, and the only way libvirt can guarantee the MAC address of a hostdev network device is to use , whose main purpose is to configure the device's MAC address before handing the device to QEMU. (note that in turn requires that the network device be an SRIOV VF (Virtual Function), as that is the only type of network device whose MAC address we can set in a way that will survive the device's driver init in the guest). It has recently come up that some users are unable to use because they are running in a container environment where libvirt doesn't have the necessary privileges or resources to set the VF's MAC address (because setting the VF MAC is done via the same device's PF (Physical Function), and the PF is not exposed to libvirt's container). At the same time, these users *are* able to set the VF's MAC address themselves in advance of staring up libvirt in the container. So they could theoretically use the feature if libvirt just skipped the "setting the MAC address" part. Fortunately, that is *exactly* the difference between (which must be a "hostdev VF") and (a "plain hostdev" - it could be *any* PCI device; libvirt doesn't know what type of PCI device it is, and doesn't care). But what is still needed is for libvirt to provide a small bit of information on the QEMU commandline argument for the hostdev, telling QEMU that this device will be part of a team ("failover pair"), and the id of the other device in the pair. To make both of those goals simultaneously possible, this patch adds support for the element to plain - libvirt doesn't try to set any MAC addresses, and QEMU gets the extra commandline argument it needs) (actually, this patch adds only the parsing/formatting of the element in . The next patch will actually wire that into the qemu driver.) Signed-off-by: Laine Stump Reviewed-by: Michal Privoznik --- docs/formatdomain.rst | 51 +++++++++++++++ docs/schemas/domaincommon.rng | 3 + src/conf/domain_conf.c | 7 ++ src/conf/domain_conf.h | 1 + src/conf/domain_validate.c | 19 ++++++ .../net-virtio-teaming-hostdev.xml | 64 +++++++++++++++++++ .../net-virtio-teaming-hostdev.xml | 1 + tests/qemuxml2xmltest.c | 3 + 8 files changed, 149 insertions(+) create mode 100644 tests/qemuxml2argvdata/net-virtio-teaming-hostdev.xml create mode 120000 tests/qemuxml2xmloutdata/net-virtio-teaming-hostdev.xml diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index 2493be595f..eafd6b3396 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -4837,6 +4837,22 @@ support in the hypervisor and the guest network driver). ... +The second interface in this example is referencing a network that is +a pool of SRIOV VFs (i.e. a "hostdev network"). You could instead +directly reference an SRIOV VF device: + +:: + + ... + + +
+ + + + + ... + The ```` element required attribute ``type`` will be set to either ``"persistent"`` to indicate a device that should always be present in the domain, or ``"transient"`` to indicate a device that may periodically be @@ -4858,6 +4874,41 @@ once migration is completed; while migration is taking place, network traffic will use the virtio NIC. (Of course the emulated virtio NIC and the hostdev NIC must be connected to the same subnet for bonding to work properly). +:since:`Since 7.1.0` The ```` element can also be added to a +plain ```` device. + +:: + + ... + + +
+ + + + + ... + +This device must be a network device, but not necessarily an SRIOV +VF. Using plain ```` rather than ```` or ```` is useful if the +device that will be assigned with VFIO is a standard NIC (not a VF) or +if libvirt doesn't have the necessary resources and privileges to set +the VF's MAC address (e.g. if libvirt is running unprivileged, or in a +container). This of course means that the user (or another +application) is responsible for setting the MAC address of the device +in a way such that it will survive guest driver initialization. For +standard NICs (i.e. not an SRIOV VF) this probably means that the +NIC's factory-programmed MAC address will need to be used for the +teaming pair (since any driver init in the guest will reset the MAC +back to factory). If it is an SRIOV VF, then its MAC address will need +to be set via the VF's PF, e.g. if you are going to use VF 2 of the PF +enp2s0f1, you would use something like this command: + +:: + + ip link set enp2s0f1 vf 2 mac 52:54:00:11:22:33 + NB1: Since you must know the alias name of the virtio NIC when configuring the hostdev NIC, it will need to be manually set in the virtio NIC's configuration (as with all other manually set alias names, this means it must start with diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index 31960fb7cf..e6de934456 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -5156,6 +5156,9 @@ + + + diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 3fe8517f39..17e0d1ed31 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -3024,6 +3024,8 @@ void virDomainHostdevDefClear(virDomainHostdevDefPtr def) if (!def->parentnet) virDomainDeviceInfoFree(def->info); + virDomainNetTeamingInfoFree(def->teaming); + switch (def->mode) { case VIR_DOMAIN_HOSTDEV_MODE_CAPABILITIES: switch ((virDomainHostdevCapsType) def->source.caps.type) { @@ -15015,6 +15017,9 @@ virDomainHostdevDefParseXML(virDomainXMLOptionPtr xmlopt, } } + if (virDomainNetTeamingInfoParseXML(ctxt, &def->teaming) < 0) + goto error; + return def; error: @@ -27433,6 +27438,8 @@ virDomainHostdevDefFormat(virBufferPtr buf, break; } + virDomainNetTeamingInfoFormat(def->teaming, buf); + if (def->readonly) virBufferAddLit(buf, "\n"); if (def->shareable) diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index fb695a212b..e263e6098b 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -354,6 +354,7 @@ struct _virDomainHostdevDef { virDomainHostdevCaps caps; } source; virDomainHostdevOrigStates origstates; + virDomainNetTeamingInfoPtr teaming; virDomainDeviceInfoPtr info; /* Guest address */ }; diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c index 703946b3e5..b47ecba86b 100644 --- a/src/conf/domain_validate.c +++ b/src/conf/domain_validate.c @@ -1585,6 +1585,25 @@ virDomainHostdevDefValidate(const virDomainHostdevDef *hostdev) break; } } + + if (hostdev->teaming) { + if (hostdev->teaming->type != VIR_DOMAIN_NET_TEAMING_TYPE_TRANSIENT) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("teaming hostdev devices must have type='transient'")); + return -1; + } + if (!hostdev->teaming->persistent) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("missing required persistent attribute in hostdev teaming element")); + return -1; + } + if (hostdev->mode != VIR_DOMAIN_HOSTDEV_MODE_SUBSYS || + hostdev->source.subsys.type != VIR_DOMAIN_HOSTDEV_SUBSYS_TYPE_PCI) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("teaming is only supported for pci hostdev devices")); + return -1; + } + } return 0; } diff --git a/tests/qemuxml2argvdata/net-virtio-teaming-hostdev.xml b/tests/qemuxml2argvdata/net-virtio-teaming-hostdev.xml new file mode 100644 index 0000000000..a7edab63bd --- /dev/null +++ b/tests/qemuxml2argvdata/net-virtio-teaming-hostdev.xml @@ -0,0 +1,64 @@ + + QEMUGuest1 + c7a5fdbd-edaf-9455-926a-d65c16db1809 + 219100 + 219100 + 1 + + hvm + + + + destroy + restart + destroy + + /usr/bin/qemu-system-i386 + + + + +
+ + +
+ + + +
+ + + + + + +
+ + + + + + +
+ + + + + +
+ + +
+ + + +
+ + +
+ + +
+ + + diff --git a/tests/qemuxml2xmloutdata/net-virtio-teaming-hostdev.xml b/tests/qemuxml2xmloutdata/net-virtio-teaming-hostdev.xml new file mode 120000 index 0000000000..f7a3c3ada0 --- /dev/null +++ b/tests/qemuxml2xmloutdata/net-virtio-teaming-hostdev.xml @@ -0,0 +1 @@ +../qemuxml2argvdata/net-virtio-teaming-hostdev.xml \ No newline at end of file diff --git a/tests/qemuxml2xmltest.c b/tests/qemuxml2xmltest.c index a00ebd7d76..5cd945f28f 100644 --- a/tests/qemuxml2xmltest.c +++ b/tests/qemuxml2xmltest.c @@ -438,6 +438,9 @@ mymain(void) DO_TEST("net-virtio-teaming-network", QEMU_CAPS_VIRTIO_NET_FAILOVER, QEMU_CAPS_DEVICE_VFIO_PCI); + DO_TEST("net-virtio-teaming-hostdev", + QEMU_CAPS_VIRTIO_NET_FAILOVER, + QEMU_CAPS_DEVICE_VFIO_PCI); DO_TEST_CAPS_LATEST("net-isolated-port"); DO_TEST("net-hostdev", NONE); DO_TEST("net-hostdev-bootorder", NONE);