On 9/2/20 3:25 PM, Jonathon Jongsma wrote:

This patch adds new schema and adds support for parsing and formatting domain configurations that include vdpa devices.

vDPA network devices allow high-performance networking in a virtual machine by providing a wire-speed data path. These devices require a vendor-specific host driver but the data path follows the virtio specification.

When a device on the host is bound to an appropriate vendor-specific driver, it will create a chardev on the host at e.g. /dev/vhost-vdpa-0. That chardev path can then be used to define a new interface with type='vdpa'.

Signed-off-by: Jonathon Jongsma <jjongsma@redhat.com> --- docs/formatdomain.rst | 23 +++++++++++++++++++ docs/schemas/domaincommon.rng | 15 ++++++++++++ src/conf/domain_conf.c | 32 ++++++++++++++++++++++++++ src/conf/domain_conf.h | 4 ++++ src/conf/netdev_bandwidth_conf.c | 1 + src/libxl/libxl_conf.c | 1 + src/libxl/xen_common.c | 1 + src/lxc/lxc_controller.c | 1 + src/lxc/lxc_driver.c | 3 +++ src/lxc/lxc_process.c | 1 + src/qemu/qemu_command.c | 3 +++ src/qemu/qemu_domain.c | 4 +++- src/qemu/qemu_hotplug.c | 3 +++ src/qemu/qemu_interface.c | 2 ++ src/qemu/qemu_process.c | 1 +

../src/qemu/qemu_process.c: In function ?qemuProcessNotifyNets?: ../src/qemu/qemu_process.c:3323:9: error: enumeration value ?VIR_DOMAIN_NET_TYPE_VDPA? not handled in switch [-Werror=switch] 3323 | switch (virDomainNetGetActualType(net)) { | ^~~~~~ (this is a switch I recently added and only pushed yesterday, so you probably just haven't rebased your branch since then. The VDPA switch in this case can be empty)

src/qemu/qemu_validate.c | 1 + src/vmx/vmx.c | 1 + tests/qemuxml2argvdata/net-vdpa.xml | 28 +++++++++++++++++++++++ tests/qemuxml2xmloutdata/net-vdpa.xml | 33 +++++++++++++++++++++++++++ tests/qemuxml2xmltest.c | 1 + tools/virsh-domain.c | 1 + 21 files changed, 159 insertions(+), 1 deletion(-) create mode 100644 tests/qemuxml2argvdata/net-vdpa.xml create mode 100644 tests/qemuxml2xmloutdata/net-vdpa.xml

diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index 1979dfb8d3..18d0e28aa1 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -4637,6 +4637,29 @@ or stopping the guest. </devices> ...

+:anchor:`<a id="elementsNICSVDPA"/>` + +vDPA devices +^^^^^^^^^^^^ + +A vDPA network device can be used to provide wire speed network performance within a +domain. A vDPA device is a specialized type of network device that uses a +datapath that complies with the virtio specification but has a vendor-specific +control path. To use such a device with libvirt, the host device must already +be bound to the appropriate device-specific vDPA driver. This creates a vDPA +char device (e.g. /dev/vhost-vdpa-0) that can be used to assign the device to +a libvirt domain.

You need to have ":since:`Since 6.8.0`" at the end of the paragraph Also, this isn't the right place for it, but maybe in a knowledgebase article we should have more detailed information about what kind of hardware is necessary, and how to create the vdpa device by binding the vdpa driver, etc. (doesn't need to be produced right away, but shouldn't be forgotten about)

+ +:: + + ... + <devices> + <interface type='vdpa'> + <source dev='/dev/vhost-vdpa-0'/> + </interface> + </devices> + ... + :anchor:`<a id="elementsTeaming"/>`

Teaming a virtio/hostdev NIC pair diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index a1d6d19e2f..4708e3550f 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -3111,6 +3111,21 @@ <ref name="interface-options"/> </interleave> </group> + + <group> + <attribute name="type"> + <value>vdpa</value> + </attribute> + <interleave> + <element name="source"> + <attribute name="dev"> + <ref name="deviceName"/> + </attribute> + </element> + <ref name="interface-options"/> + </interleave> + </group> + </choice> <optional> <attribute name="trustGuestRxFilters"> diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 72ac4f4191..dbabbbe900 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -550,6 +550,7 @@ VIR_ENUM_IMPL(virDomainNet, "direct", "hostdev", "udp", + "vdpa", );

VIR_ENUM_IMPL(virDomainNetModel, @@ -2502,6 +2503,10 @@ virDomainNetDefClear(virDomainNetDefPtr def) def->data.vhostuser = NULL; break;

+ case VIR_DOMAIN_NET_TYPE_VDPA: + VIR_FREE(def->data.vdpa.devicepath); + break; + case VIR_DOMAIN_NET_TYPE_SERVER: case VIR_DOMAIN_NET_TYPE_CLIENT: case VIR_DOMAIN_NET_TYPE_MCAST: @@ -12036,6 +12041,7 @@ virDomainNetDefParseXML(virDomainXMLOptionPtr xmlopt, g_autofree char *vhost_path = NULL; g_autofree char *teamingType = NULL; g_autofree char *teamingPersistent = NULL; + g_autofree char *vdpa_dev = NULL;

I think it's okay to just use the existing char *dev, since that is also used for <source dev='blah'/> (of type='direct' devices).

const char *prefix = xmlopt ? xmlopt->config.netPrefix : NULL;

if (!(def = virDomainNetDefNew(xmlopt))) @@ -12129,6 +12135,10 @@ virDomainNetDefParseXML(virDomainXMLOptionPtr xmlopt, if (virDomainChrSourceReconnectDefParseXML(&reconnect, cur, ctxt) < 0) goto error;

+ } else if (!vdpa_dev + && def->type == VIR_DOMAIN_NET_TYPE_VDPA + && virXMLNodeNameEqual(cur, "source")) { + vdpa_dev = virXMLPropString(cur, "dev"); } else if (!def->virtPortProfile && virXMLNodeNameEqual(cur, "virtualport")) { if (def->type == VIR_DOMAIN_NET_TYPE_NETWORK) { @@ -12386,6 +12396,16 @@ virDomainNetDefParseXML(virDomainXMLOptionPtr xmlopt, } break;

+ case VIR_DOMAIN_NET_TYPE_VDPA: + if (vdpa_dev == NULL) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("No <source> 'dev' attribute " + "specified with <interface type='vdpa'/>")); + goto error; + } + def->data.vdpa.devicepath = g_steal_pointer(&vdpa_dev); + break; + case VIR_DOMAIN_NET_TYPE_BRIDGE: if (bridge == NULL) { virReportError(VIR_ERR_INTERNAL_ERROR, "%s", @@ -12775,6 +12795,7 @@ virDomainNetDefParseXML(virDomainXMLOptionPtr xmlopt, case VIR_DOMAIN_NET_TYPE_DIRECT: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: break; case VIR_DOMAIN_NET_TYPE_LAST: default: @@ -26881,6 +26902,14 @@ virDomainNetDefFormat(virBufferPtr buf, } break;

+ case VIR_DOMAIN_NET_TYPE_VDPA: + if (def->data.vdpa.devicepath) { + virBufferEscapeString(buf, "<source dev='%s'", + def->data.vdpa.devicepath); + sourceLines++; + } + break; + case VIR_DOMAIN_NET_TYPE_USER: case VIR_DOMAIN_NET_TYPE_LAST: break; @@ -31094,6 +31123,7 @@ virDomainNetGetActualVirtPortProfile(const virDomainNetDef *iface) case VIR_DOMAIN_NET_TYPE_MCAST: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: default: return NULL; @@ -31926,6 +31956,7 @@ virDomainNetTypeSharesHostView(const virDomainNetDef *net) case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: break; } @@ -32190,6 +32221,7 @@ virDomainNetDefActualToNetworkPort(virDomainDefPtr dom, case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_USER: case VIR_DOMAIN_NET_TYPE_VHOSTUSER: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, _("Unexpected network port type %s"), virDomainNetTypeToString(virDomainNetGetActualType(iface))); diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index 14a376350c..1a1caad96d 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -875,6 +875,7 @@ typedef enum { VIR_DOMAIN_NET_TYPE_DIRECT, VIR_DOMAIN_NET_TYPE_HOSTDEV, VIR_DOMAIN_NET_TYPE_UDP, + VIR_DOMAIN_NET_TYPE_VDPA,

VIR_DOMAIN_NET_TYPE_LAST } virDomainNetType; @@ -1048,6 +1049,9 @@ struct _virDomainNetDef { */ virDomainActualNetDefPtr actual; } network; + struct { + char *devicepath; + } vdpa; struct { char *brname; } bridge; diff --git a/src/conf/netdev_bandwidth_conf.c b/src/conf/netdev_bandwidth_conf.c index 396ac62019..4eb12e2951 100644 --- a/src/conf/netdev_bandwidth_conf.c +++ b/src/conf/netdev_bandwidth_conf.c @@ -315,6 +315,7 @@ bool virNetDevSupportsBandwidth(virDomainNetType type) case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: break; } diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c index befd5eb965..23f1cb213e 100644 --- a/src/libxl/libxl_conf.c +++ b/src/libxl/libxl_conf.c @@ -1378,6 +1378,7 @@ libxlMakeNic(virDomainDefPtr def, case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_DIRECT: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, _("unsupported interface type %s"), diff --git a/src/libxl/xen_common.c b/src/libxl/xen_common.c index 56702a2a76..183b09671a 100644 --- a/src/libxl/xen_common.c +++ b/src/libxl/xen_common.c @@ -1792,6 +1792,7 @@ xenFormatNet(virConnectPtr conn, case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_USER: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, _("Unsupported net type '%s'"), virDomainNetTypeToString(net->type)); return -1; diff --git a/src/lxc/lxc_controller.c b/src/lxc/lxc_controller.c index 0a496fb788..be7cc7cb11 100644 --- a/src/lxc/lxc_controller.c +++ b/src/lxc/lxc_controller.c @@ -422,6 +422,7 @@ static int virLXCControllerGetNICIndexes(virLXCControllerPtr ctrl) case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, _("Unsupported net type %s"), virDomainNetTypeToString(actualType)); diff --git a/src/lxc/lxc_driver.c b/src/lxc/lxc_driver.c index a530488dd2..4d3c5d9f63 100644 --- a/src/lxc/lxc_driver.c +++ b/src/lxc/lxc_driver.c @@ -3504,6 +3504,7 @@ lxcDomainAttachDeviceNetLive(virLXCDriverPtr driver, case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", _("Network device type is not supported")); goto cleanup; @@ -3558,6 +3559,7 @@ lxcDomainAttachDeviceNetLive(virLXCDriverPtr driver, case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: default: /* no-op */ @@ -3999,6 +4001,7 @@ lxcDomainDetachDeviceNetLive(virDomainObjPtr vm, case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", _("Only bridged veth devices can be detached")); goto cleanup; diff --git a/src/lxc/lxc_process.c b/src/lxc/lxc_process.c index 16969dbf33..d103ec6666 100644 --- a/src/lxc/lxc_process.c +++ b/src/lxc/lxc_process.c @@ -606,6 +606,7 @@ virLXCProcessSetupInterfaces(virLXCDriverPtr driver, case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_LAST: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_INTERNAL_ERROR, _("Unsupported network type %s"), virDomainNetTypeToString(type)); diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index bd98b0a97c..7b7176eb72 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -3691,6 +3691,7 @@ qemuBuildHostNetStr(virDomainNetDefPtr net, return NULL; break;

+ case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_HOSTDEV: /* Should have been handled earlier via PCI/USB hotplug code. */ case VIR_DOMAIN_NET_TYPE_LAST: @@ -8107,6 +8108,7 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, case VIR_DOMAIN_NET_TYPE_MCAST: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: /* nada */ break; @@ -8143,6 +8145,7 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: /* These types don't use a network device on the host, but * instead use some other type of connection to the emulated diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index b1884b6c84..680e7d5bf8 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -5174,7 +5174,8 @@ qemuDomainDeviceNetDefPostParse(virDomainNetDefPtr net, const virDomainDef *def, virQEMUCapsPtr qemuCaps) { - if (net->type != VIR_DOMAIN_NET_TYPE_HOSTDEV && + if (net->type != VIR_DOMAIN_NET_TYPE_VDPA && + net->type != VIR_DOMAIN_NET_TYPE_HOSTDEV && !virDomainNetGetModelString(net) && virDomainNetResolveActualType(net) != VIR_DOMAIN_NET_TYPE_HOSTDEV) net->model = qemuDomainDefaultNetModel(def, qemuCaps); @@ -9308,6 +9309,7 @@ qemuDomainNetSupportsMTU(virDomainNetType type) case VIR_DOMAIN_NET_TYPE_DIRECT: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: break; } diff --git a/src/qemu/qemu_hotplug.c b/src/qemu/qemu_hotplug.c index e2c6e14c2e..78dd5e9f19 100644 --- a/src/qemu/qemu_hotplug.c +++ b/src/qemu/qemu_hotplug.c @@ -1340,6 +1340,7 @@ qemuDomainAttachNetDevice(virQEMUDriverPtr driver, case VIR_DOMAIN_NET_TYPE_MCAST: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: virReportError(VIR_ERR_OPERATION_UNSUPPORTED, _("hotplug of interface type of %s is not implemented yet"), @@ -3389,6 +3390,7 @@ qemuDomainChangeNetFilter(virDomainObjPtr vm, case VIR_DOMAIN_NET_TYPE_DIRECT: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, _("filters not supported on interfaces of type %s"), virDomainNetTypeToString(virDomainNetGetActualType(newdev))); @@ -3726,6 +3728,7 @@ qemuDomainChangeNet(virQEMUDriverPtr driver,

case VIR_DOMAIN_NET_TYPE_VHOSTUSER: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_OPERATION_UNSUPPORTED, _("unable to change config on '%s' network type"), virDomainNetTypeToString(newdev->type)); diff --git a/src/qemu/qemu_interface.c b/src/qemu/qemu_interface.c index 10a87a2528..33157dbbed 100644 --- a/src/qemu/qemu_interface.c +++ b/src/qemu/qemu_interface.c @@ -118,6 +118,7 @@ qemuInterfaceStartDevice(virDomainNetDefPtr net) case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: /* these types all require no action */ break; @@ -203,6 +204,7 @@ qemuInterfaceStopDevice(virDomainNetDefPtr net) case VIR_DOMAIN_NET_TYPE_UDP: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: /* these types all require no action */ break; diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index cfe09d6326..e56e3bf449 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -7531,6 +7531,7 @@ void qemuProcessStop(virQEMUDriverPtr driver, case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: /* No special cleanup procedure for these types. */ break; diff --git a/src/qemu/qemu_validate.c b/src/qemu/qemu_validate.c index 070f1c962b..25f7866e5c 100644 --- a/src/qemu/qemu_validate.c +++ b/src/qemu/qemu_validate.c @@ -1145,6 +1145,7 @@ qemuValidateNetSupportsCoalesce(virDomainNetType type) case VIR_DOMAIN_NET_TYPE_MCAST: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: break; } diff --git a/src/vmx/vmx.c b/src/vmx/vmx.c index 4b1b04c6e1..6e0fd61f60 100644 --- a/src/vmx/vmx.c +++ b/src/vmx/vmx.c @@ -3833,6 +3833,7 @@ virVMXFormatEthernet(virDomainNetDefPtr def, int controller, case VIR_DOMAIN_NET_TYPE_DIRECT: case VIR_DOMAIN_NET_TYPE_HOSTDEV: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: virReportError(VIR_ERR_CONFIG_UNSUPPORTED, _("Unsupported net type '%s'"), virDomainNetTypeToString(def->type)); return -1; diff --git a/tests/qemuxml2argvdata/net-vdpa.xml b/tests/qemuxml2argvdata/net-vdpa.xml new file mode 100644 index 0000000000..30cca7eb6e --- /dev/null +++ b/tests/qemuxml2argvdata/net-vdpa.xml @@ -0,0 +1,28 @@ +<domain type='qemu'> + <name>QEMUGuest1</name> + <uuid>c7a5fdbd-edaf-9455-926a-d65c16db1809</uuid> + <memory unit='KiB'>219136</memory> + <currentMemory unit='KiB'>219136</currentMemory> + <vcpu placement='static'>1</vcpu> + <os> + <type arch='i686' machine='pc'>hvm</type> + <boot dev='hd'/> + </os> + <clock offset='utc'/> + <on_poweroff>destroy</on_poweroff> + <on_reboot>restart</on_reboot> + <on_crash>destroy</on_crash> + <devices> + <emulator>/usr/bin/qemu-system-i386</emulator> + <controller type='usb' index='0'/> + <controller type='ide' index='0'/> + <controller type='pci' index='0' model='pci-root'/> + <interface type='vdpa'> + <mac address='52:54:00:95:db:c0'/> + <source dev='/dev/vhost-vdpa-0'/> + </interface> + <input type='mouse' bus='ps2'/> + <input type='keyboard' bus='ps2'/> + <memballoon model='none'/> + </devices> +</domain> diff --git a/tests/qemuxml2xmloutdata/net-vdpa.xml b/tests/qemuxml2xmloutdata/net-vdpa.xml new file mode 100644 index 0000000000..bb2782e848 --- /dev/null +++ b/tests/qemuxml2xmloutdata/net-vdpa.xml @@ -0,0 +1,33 @@ +<domain type='qemu'> + <name>QEMUGuest1</name> + <uuid>c7a5fdbd-edaf-9455-926a-d65c16db1809</uuid> + <memory unit='KiB'>219136</memory> + <currentMemory unit='KiB'>219136</currentMemory> + <vcpu placement='static'>1</vcpu> + <os> + <type arch='i686' machine='pc'>hvm</type> + <boot dev='hd'/> + </os> + <clock offset='utc'/> + <on_poweroff>destroy</on_poweroff> + <on_reboot>restart</on_reboot> + <on_crash>destroy</on_crash> + <devices> + <emulator>/usr/bin/qemu-system-i386</emulator> + <controller type='usb' index='0'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x01' function='0x2'/> + </controller> + <controller type='ide' index='0'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x01' function='0x1'/> + </controller> + <controller type='pci' index='0' model='pci-root'/> + <interface type='vdpa'> + <mac address='52:54:00:95:db:c0'/> + <source dev='/dev/vhost-vdpa-0'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' function='0x0'/> + </interface> + <input type='mouse' bus='ps2'/> + <input type='keyboard' bus='ps2'/> + <memballoon model='none'/> + </devices> +</domain> diff --git a/tests/qemuxml2xmltest.c b/tests/qemuxml2xmltest.c index 6eb008c8d2..a2601d045e 100644 --- a/tests/qemuxml2xmltest.c +++ b/tests/qemuxml2xmltest.c @@ -497,6 +497,7 @@ mymain(void) DO_TEST("net-mtu", NONE); DO_TEST("net-coalesce", NONE); DO_TEST("net-many-models", NONE); + DO_TEST("net-vdpa", NONE);

DO_TEST("serial-tcp-tlsx509-chardev", NONE); DO_TEST("serial-tcp-tlsx509-chardev-notls", NONE); diff --git a/tools/virsh-domain.c b/tools/virsh-domain.c index 36581d2c31..7949acff09 100644 --- a/tools/virsh-domain.c +++ b/tools/virsh-domain.c @@ -1006,6 +1006,7 @@ cmdAttachInterface(vshControl *ctl, const vshCmd *cmd) case VIR_DOMAIN_NET_TYPE_CLIENT: case VIR_DOMAIN_NET_TYPE_MCAST: case VIR_DOMAIN_NET_TYPE_UDP: + case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_LAST: vshError(ctl, _("No support for %s in command 'attach-interface'"),

Reviewed-by: Laine Stump <laine@redhat.com> with the build error fixed and the "since" line added to the formatdomain.rst. Whether or not to conflate char *dev and char *vdpa_dev is optional, depending on your opinion, and a more detailed knowledgebase article might make more sense after being able to actually try it out on some real hardware :-)

On 9/2/20 3:25 PM, Jonathon Jongsma wrote:

Recent versions of qemu added the -netdev vhost-vdpa device. This capability allows libvirt to know whether this is supported.

Looks like you haven't rebased since the capabilities file was added for qemu 5.2.0, as the capabilitiestest fails. With that fixed, Reviewed-by: Laine Stump <laine@redhat.com>

Signed-off-by: Jonathon Jongsma <jjongsma@redhat.com> --- src/qemu/qemu_capabilities.c | 4 ++++ src/qemu/qemu_capabilities.h | 3 +++ tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml | 1 + 3 files changed, 8 insertions(+)

diff --git a/src/qemu/qemu_capabilities.c b/src/qemu/qemu_capabilities.c index 2cc0c61588..b19928f68d 100644 --- a/src/qemu/qemu_capabilities.c +++ b/src/qemu/qemu_capabilities.c @@ -597,6 +597,9 @@ VIR_ENUM_IMPL(virQEMUCaps, "spapr-tpm-proxy", "numa.hmat", "blockdev-hostdev-scsi", + + /* 380 */ + "netdev.vhost-vdpa", );

@@ -1526,6 +1529,7 @@ static struct virQEMUCapsStringFlags virQEMUCapsQMPSchemaQueries[] = { { "migrate-set-parameters/arg-type/downtime-limit", QEMU_CAPS_MIGRATION_PARAM_DOWNTIME }, { "migrate-set-parameters/arg-type/xbzrle-cache-size", QEMU_CAPS_MIGRATION_PARAM_XBZRLE_CACHE_SIZE }, { "set-numa-node/arg-type/+hmat-lb", QEMU_CAPS_NUMA_HMAT }, + { "netdev_add/arg-type/+vhost-vdpa", QEMU_CAPS_NETDEV_VHOST_VDPA }, };

typedef struct _virQEMUCapsObjectTypeProps virQEMUCapsObjectTypeProps; diff --git a/src/qemu/qemu_capabilities.h b/src/qemu/qemu_capabilities.h index 5d08941538..b6110f1c34 100644 --- a/src/qemu/qemu_capabilities.h +++ b/src/qemu/qemu_capabilities.h @@ -578,6 +578,9 @@ typedef enum { /* virQEMUCapsFlags grouping marker for syntax-check */ QEMU_CAPS_NUMA_HMAT, /* -numa hmat */ QEMU_CAPS_BLOCKDEV_HOSTDEV_SCSI, /* -blockdev used for (i)SCSI hostdevs */

+ /* 380 */ + QEMU_CAPS_NETDEV_VHOST_VDPA, /* -netdev vhost-vdpa*/ + QEMU_CAPS_LAST /* this must always be the last item */ } virQEMUCapsFlags;

diff --git a/tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml b/tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml index 7496ff1379..0fd2f3b816 100644 --- a/tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml @@ -242,6 +242,7 @@ <flag name='intel-iommu.aw-bits'/> <flag name='numa.hmat'/> <flag name='blockdev-hostdev-scsi'/> + <flag name='netdev.vhost-vdpa'/> <version>5001000</version> <kvmVersion>0</kvmVersion> <microcodeVersion>43100242</microcodeVersion>

On 9/2/20 3:25 PM, Jonathon Jongsma wrote:

Enable <interface type='vdpa'> for qemu domains. This provides basic support and does not support hotplug or migration.

Is there something specifically preventing hotplug, or you just haven't implemented it yet? (How does that work with FD passing, anyway? I haven't really looked at the details of FD passing...) If hotplug is possible, then I really think that needs to be implemented in the initial patch set. Same question for migration - is it not possible with these devices, or we're just not certain or are missing some pieces so we're disabling it out of caution? For migration it's even more important to implement it with the initial patches if it works at all. Otherwise, once we do implement it, we'll have to have a way of detecting whether or not the destination of a migration supports migrating vdpa devices. (I can see where it simply may not work, since I guess the hardware's memory is used for packet buffers, right?)

Signed-off-by: Jonathon Jongsma <jjongsma@redhat.com> --- src/qemu/qemu_command.c | 28 ++++++++++++-- src/qemu/qemu_command.h | 3 +- src/qemu/qemu_domain.c | 6 +++ src/qemu/qemu_hotplug.c | 12 +++--- src/qemu/qemu_interface.c | 23 ++++++++++++ src/qemu/qemu_interface.h | 2 + src/qemu/qemu_migration.c | 10 ++++- .../net-vdpa.x86_64-latest.args | 37 +++++++++++++++++++ tests/qemuxml2argvmock.c | 11 +++++- tests/qemuxml2argvtest.c | 1 + 10 files changed, 122 insertions(+), 11 deletions(-) create mode 100644 tests/qemuxml2argvdata/net-vdpa.x86_64-latest.args

diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index 7b7176eb72..b9830292ee 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -3553,7 +3553,8 @@ qemuBuildHostNetStr(virDomainNetDefPtr net, size_t tapfdSize, char **vhostfd, size_t vhostfdSize, - const char *slirpfd) + const char *slirpfd, + const char *vdpadev) { bool is_tap = false; virDomainNetType netType = virDomainNetGetActualType(net); @@ -3692,6 +3693,12 @@ qemuBuildHostNetStr(virDomainNetDefPtr net, break;

case VIR_DOMAIN_NET_TYPE_VDPA: + /* Caller will pass the fd to qemu with add-fd */ + if (virJSONValueObjectCreate(&netprops, "s:type", "vhost-vdpa", NULL) < 0 || + virJSONValueObjectAppendString(netprops, "vhostdev", vdpadev) < 0) + return NULL; + break; + case VIR_DOMAIN_NET_TYPE_HOSTDEV: /* Should have been handled earlier via PCI/USB hotplug code. */ case VIR_DOMAIN_NET_TYPE_LAST: @@ -8017,6 +8024,8 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, char **tapfdName = NULL; char **vhostfdName = NULL; g_autofree char *slirpfdName = NULL; + g_autofree char *vdpafdName = NULL; + int vdpafd = -1; virDomainNetType actualType = virDomainNetGetActualType(net); const virNetDevBandwidth *actualBandwidth; bool requireNicdev = false; @@ -8102,13 +8111,17 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver,

break;

+ case VIR_DOMAIN_NET_TYPE_VDPA: + if ((vdpafd = qemuInterfaceVDPAConnect(net)) < 0) + goto cleanup; + break; + case VIR_DOMAIN_NET_TYPE_USER: case VIR_DOMAIN_NET_TYPE_SERVER: case VIR_DOMAIN_NET_TYPE_CLIENT: case VIR_DOMAIN_NET_TYPE_MCAST: case VIR_DOMAIN_NET_TYPE_INTERNAL: case VIR_DOMAIN_NET_TYPE_UDP: - case VIR_DOMAIN_NET_TYPE_VDPA: case VIR_DOMAIN_NET_TYPE_LAST: /* nada */ break; @@ -8225,13 +8238,22 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, vhostfd[i] = -1; }

+ if (vdpafd > 0) { + virCommandPassFD(cmd, vdpafd, VIR_COMMAND_PASS_FD_CLOSE_PARENT); + g_autofree char *fdset = qemuVirCommandGetFDSet(cmd, vdpafd); + if (!fdset) + goto cleanup; + virCommandAddArgList(cmd, "-add-fd", fdset, NULL); + vdpafdName = qemuVirCommandGetDevSet(cmd, vdpafd); + } + if (chardev) virCommandAddArgList(cmd, "-chardev", chardev, NULL);

if (!(hostnetprops = qemuBuildHostNetStr(net, tapfdName, tapfdSize, vhostfdName, vhostfdSize, - slirpfdName))) + slirpfdName, vdpafdName))) goto cleanup;

if (!(host = virQEMUBuildNetdevCommandlineFromJSON(hostnetprops, diff --git a/src/qemu/qemu_command.h b/src/qemu/qemu_command.h index 89d99b111f..8db51f93b1 100644 --- a/src/qemu/qemu_command.h +++ b/src/qemu/qemu_command.h @@ -99,7 +99,8 @@ virJSONValuePtr qemuBuildHostNetStr(virDomainNetDefPtr net, size_t tapfdSize, char **vhostfd, size_t vhostfdSize, - const char *slirpfd); + const char *slirpfd, + const char *vdpadev);

/* Current, best practice */ char *qemuBuildNicDevStr(virDomainDefPtr def, diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index 680e7d5bf8..b94a181043 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -4488,6 +4488,12 @@ qemuDomainValidateActualNetDef(const virDomainNetDef *net, macstr, virDomainNetTypeToString(actualType)); return -1; } + if (actualType == VIR_DOMAIN_NET_TYPE_VDPA && + !virQEMUCapsGet(qemuCaps, QEMU_CAPS_NETDEV_VHOST_VDPA)) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("vDPA device is not supported with this QEMU binary")); + return -1; + }

Note that this function isn't called until the domain is being started. Since a type='network' interface can't have an ActualType of VDPA, we can do this validation at domain definition time, in qemuValidateDomainDeviceDefNetwork() (writing this, and looking at the other functions called, points out to me that those validation functions *really* need more consistent names, and also that qemuDomainValidateActualNetDef() should probably be moved from qemu_domain.c to qemu_validate.c. But neither of those is your problem; just move this check to the other function so it happens at domain define time rather than domain start time.

return 0; }

diff --git a/src/qemu/qemu_hotplug.c b/src/qemu/qemu_hotplug.c index 78dd5e9f19..45c07a7f4e 100644 --- a/src/qemu/qemu_hotplug.c +++ b/src/qemu/qemu_hotplug.c @@ -1389,7 +1389,7 @@ qemuDomainAttachNetDevice(virQEMUDriverPtr driver, if (!(netprops = qemuBuildHostNetStr(net, tapfdName, tapfdSize, vhostfdName, vhostfdSize, - slirpfdName))) + slirpfdName, NULL))) goto cleanup;

qemuDomainObjEnterMonitor(driver, vm); @@ -3484,8 +3484,9 @@ qemuDomainChangeNet(virQEMUDriverPtr driver, olddev = *devslot;

oldType = virDomainNetGetActualType(olddev); - if (oldType == VIR_DOMAIN_NET_TYPE_HOSTDEV) { - /* no changes are possible to a type='hostdev' interface */ + if (oldType == VIR_DOMAIN_NET_TYPE_HOSTDEV || + oldType == VIR_DOMAIN_NET_TYPE_VDPA) { + /* no changes are possible to a type='hostdev' or type='vdpa' interface */ virReportError(VIR_ERR_OPERATION_UNSUPPORTED, _("cannot change config of '%s' network type"), virDomainNetTypeToString(oldType)); @@ -3672,8 +3673,9 @@ qemuDomainChangeNet(virQEMUDriverPtr driver,

newType = virDomainNetGetActualType(newdev);

- if (newType == VIR_DOMAIN_NET_TYPE_HOSTDEV) { - /* can't turn it into a type='hostdev' interface */ + if (newType == VIR_DOMAIN_NET_TYPE_HOSTDEV || + newType == VIR_DOMAIN_NET_TYPE_VDPA) { + /* can't turn it into a type='hostdev' or type='vdpa' interface */ virReportError(VIR_ERR_OPERATION_UNSUPPORTED, _("cannot change network interface type to '%s'"), virDomainNetTypeToString(newType)); diff --git a/src/qemu/qemu_interface.c b/src/qemu/qemu_interface.c index 33157dbbed..a91563dd72 100644 --- a/src/qemu/qemu_interface.c +++ b/src/qemu/qemu_interface.c @@ -641,6 +641,29 @@ qemuInterfaceBridgeConnect(virDomainDefPtr def, }

+/* qemuInterfaceVDPAConnect: + * @net: pointer to the VM's interface description + * + * returns: file descriptor of the vdpa device + * + * Called *only* called if actualType is VIR_DOMAIN_NET_TYPE_VDPA + */ +int +qemuInterfaceVDPAConnect(virDomainNetDefPtr net) +{ + int fd; + + if ((fd = open(net->data.vdpa.devicepath, O_RDWR)) < 0) { + virReportSystemError(errno, + _("Unable to open '%s' for vdpa device"), + net->data.vdpa.devicepath); + return -1; + } + + return fd; +} + + qemuSlirpPtr qemuInterfacePrepareSlirp(virQEMUDriverPtr driver, virDomainNetDefPtr net) diff --git a/src/qemu/qemu_interface.h b/src/qemu/qemu_interface.h index 3dcefc6a12..1ba24f0a6f 100644 --- a/src/qemu/qemu_interface.h +++ b/src/qemu/qemu_interface.h @@ -58,3 +58,5 @@ int qemuInterfaceOpenVhostNet(virDomainDefPtr def,

qemuSlirpPtr qemuInterfacePrepareSlirp(virQEMUDriverPtr driver, virDomainNetDefPtr net); + +int qemuInterfaceVDPAConnect(virDomainNetDefPtr net) G_GNUC_NO_INLINE; diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c index 142faa2cf9..238abadd6a 100644 --- a/src/qemu/qemu_migration.c +++ b/src/qemu/qemu_migration.c @@ -1281,7 +1281,15 @@ qemuMigrationSrcIsAllowed(virQEMUDriverPtr driver,

for (i = 0; i < vm->def->nnets; i++) { virDomainNetDefPtr net = vm->def->nets[i]; - qemuSlirpPtr slirp = QEMU_DOMAIN_NETWORK_PRIVATE(net)->slirp; + qemuSlirpPtr slirp; + + if (net->type == VIR_DOMAIN_NET_TYPE_VDPA) { + virReportError(VIR_ERR_OPERATION_INVALID, "%s", + _("a vDPA device cannot be migrated")); + return false; + } + + slirp = QEMU_DOMAIN_NETWORK_PRIVATE(net)->slirp;

Interesting that the original code didn't check the device type before looking at the slirp privateData. I guess it isn't really necessary, since that will be NULL unless type==slirp anyway, but... Maybe this should be done with a switch(virDomainNetGetActualType(net)) so that new interface types are reminded they may need to do something for this.

if (slirp && !qemuSlirpHasFeature(slirp, QEMU_SLIRP_FEATURE_MIGRATE)) { virReportError(VIR_ERR_OPERATION_INVALID, "%s", diff --git a/tests/qemuxml2argvdata/net-vdpa.x86_64-latest.args b/tests/qemuxml2argvdata/net-vdpa.x86_64-latest.args new file mode 100644 index 0000000000..8e76ac7794 --- /dev/null +++ b/tests/qemuxml2argvdata/net-vdpa.x86_64-latest.args @@ -0,0 +1,37 @@ +LC_ALL=C \ +PATH=/bin \ +HOME=/tmp/lib/domain--1-QEMUGuest1 \ +USER=test \ +LOGNAME=test \ +XDG_DATA_HOME=/tmp/lib/domain--1-QEMUGuest1/.local/share \ +XDG_CACHE_HOME=/tmp/lib/domain--1-QEMUGuest1/.cache \ +XDG_CONFIG_HOME=/tmp/lib/domain--1-QEMUGuest1/.config \ +QEMU_AUDIO_DRV=none \ +/usr/bin/qemu-system-i386 \ +-name guest=QEMUGuest1,debug-threads=on \ +-S \ +-object secret,id=masterKey0,format=raw,\ +file=/tmp/lib/domain--1-QEMUGuest1/master-key.aes \ +-machine pc,accel=tcg,usb=off,dump-guest-core=off \ +-cpu qemu64 \ +-m 214 \ +-overcommit mem-lock=off \ +-smp 1,sockets=1,cores=1,threads=1 \ +-uuid c7a5fdbd-edaf-9455-926a-d65c16db1809 \ +-display none \ +-no-user-config \ +-nodefaults \ +-chardev socket,id=charmonitor,fd=1729,server,nowait \ +-mon chardev=charmonitor,id=monitor,mode=control \ +-rtc base=utc \ +-no-shutdown \ +-no-acpi \ +-boot strict=on \ +-device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 \ +-add-fd set=0,fd=1732 \ +-netdev vhost-vdpa,vhostdev=/dev/fdset/0,id=hostnet0 \ +-device virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:95:db:c0,bus=pci.0,\ +addr=0x2 \ +-sandbox on,obsolete=deny,elevateprivileges=deny,spawn=deny,\ +resourcecontrol=deny \ +-msg timestamp=on diff --git a/tests/qemuxml2argvmock.c b/tests/qemuxml2argvmock.c index e5841bc8e3..516776697f 100644 --- a/tests/qemuxml2argvmock.c +++ b/tests/qemuxml2argvmock.c @@ -205,7 +205,7 @@ virHostGetDRMRenderNode(void)

static void (*real_virCommandPassFD)(virCommandPtr cmd, int fd, unsigned int flags);

-static const int testCommandPassSafeFDs[] = { 1730, 1731 }; +static const int testCommandPassSafeFDs[] = { 1730, 1731, 1732 };

void virCommandPassFD(virCommandPtr cmd, @@ -283,3 +283,12 @@ qemuBuildTPMOpenBackendFDs(const char *tpmdev G_GNUC_UNUSED, *cancelfd = 1731; return 0; } + + +int +qemuInterfaceVDPAConnect(virDomainNetDefPtr net G_GNUC_UNUSED) +{ + if (fcntl(1732, F_GETFD) != -1) + abort(); + return 1732; +} diff --git a/tests/qemuxml2argvtest.c b/tests/qemuxml2argvtest.c index e93948e3fc..000d6919f2 100644 --- a/tests/qemuxml2argvtest.c +++ b/tests/qemuxml2argvtest.c @@ -1446,6 +1446,7 @@ mymain(void) QEMU_CAPS_DEVICE_VFIO_PCI); DO_TEST_FAILURE("net-hostdev-fail", QEMU_CAPS_DEVICE_VFIO_PCI); + DO_TEST_CAPS_LATEST("net-vdpa");

DO_TEST("hostdev-pci-multifunction", QEMU_CAPS_KVM,

Any luck finding hardware to test it? I'm curious if all the SELinux t's are crossed and i's dotted.