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(a)redhat.com&gt; --- docs/formatdomain.rst | 24 ++++++++++++++++++++++++ docs/schemas/domaincommon.rng | 15 +++++++++++++++ src/conf/domain_conf.c | 31 +++++++++++++++++++++++++++++++ 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 | 2 ++ src/qemu/qemu_validate.c | 1 + src/vmx/vmx.c | 1 + tools/virsh-domain.c | 1 + 18 files changed, 98 insertions(+), 1 deletion(-) diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index 888db5ea29..b0c2b43dc2 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -4643,6 +4643,30 @@ 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. :since:`Since 6.8.0 (QEMU only, +requires QEMU 5.1.0 or newer)` + +:: + + ... + <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 4b7e460148..4ce485a762 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -3117,6 +3117,21 @@ <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 a91dbd4aa9..0b78ff7c70 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -554,6 +554,7 @@ VIR_ENUM_IMPL(virDomainNet, "direct", "hostdev", "udp", + "vdpa", ); VIR_ENUM_IMPL(virDomainNetModel, @@ -2505,6 +2506,10 @@ 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: @@ -12133,6 +12138,10 @@ virDomainNetDefParseXML(virDomainXMLOptionPtr xmlopt, if (virDomainChrSourceReconnectDefParseXML(&reconnect, cur, ctxt) < 0) goto error; + } else if (!dev + && def->type == VIR_DOMAIN_NET_TYPE_VDPA + && virXMLNodeNameEqual(cur, "source")) { + dev = virXMLPropString(cur, "dev"); } else if (!def->virtPortProfile && virXMLNodeNameEqual(cur, "virtualport")) { if (def->type == VIR_DOMAIN_NET_TYPE_NETWORK) { @@ -12390,6 +12399,16 @@ virDomainNetDefParseXML(virDomainXMLOptionPtr xmlopt, } break; + case VIR_DOMAIN_NET_TYPE_VDPA: + if (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(&dev); + break; + case VIR_DOMAIN_NET_TYPE_BRIDGE: if (bridge == NULL) { virReportError(VIR_ERR_INTERNAL_ERROR, "%s", @@ -12779,6 +12798,7 @@ 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: @@ -26947,6 +26967,14 @@ 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; @@ -31160,6 +31188,7 @@ 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; @@ -31992,6 +32021,7 @@ 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; } @@ -32256,6 +32286,7 @@ 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 8f1662aae0..da35aa6c2d 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -883,6 +883,7 @@ 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; @@ -1056,6 +1057,9 @@ 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 5b729a019a..b570a5a167 100644 --- a/src/libxl/libxl_conf.c +++ b/src/libxl/libxl_conf.c @@ -1391,6 +1391,7 @@ 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 c3cf485e2c..9f944dec74 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 91b59538aa..a9367f7758 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -3692,6 +3692,7 @@ 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: @@ -8132,6 +8133,7 @@ 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; @@ -8168,6 +8170,7 @@ 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 279de2997d..fe80fa9aed 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -5129,7 +5129,8 @@ 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); @@ -9323,6 +9324,7 @@ 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 fc0866c011..ade77330ff 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"), @@ -3390,6 +3391,7 @@ 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))); @@ -3727,6 +3729,7 @@ 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 cbf3d99981..b24f9060a9 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 f21b8f1585..b32b9fe20a 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -3363,6 +3363,7 @@ qemuProcessNotifyNets(virDomainDefPtr def) 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; } @@ -7591,6 +7592,7 @@ 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 3ed4039cdf..1c803c98f7 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/tools/virsh-domain.c b/tools/virsh-domain.c index 32edfc0398..ef2a353aab 100644 --- a/tools/virsh-domain.c +++ b/tools/virsh-domain.c @@ -1007,6 +1007,7 @@ 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'"), -- 2.26.2

Recent versions of qemu added the -netdev vhost-vdpa device. This capability allows libvirt to know whether this is supported. Signed-off-by: Jonathon Jongsma <jjongsma(a)redhat.com&gt; --- src/qemu/qemu_capabilities.c | 4 ++++ src/qemu/qemu_capabilities.h | 3 +++ tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml | 1 + 4 files changed, 9 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> diff --git a/tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml b/tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml index 151bd18137..e4686000a9 100644 --- a/tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_5.2.0.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>5001050</version> <kvmVersion>0</kvmVersion> <microcodeVersion>43100243</microcodeVersion> -- 2.26.2

add-fd, remove-fd, and query-fdsets provide functionality that can be used for passing fds to qemu and closing fdsets that are no longer necessary. Signed-off-by: Jonathon Jongsma <jjongsma(a)redhat.com&gt; --- src/qemu/qemu_monitor.c | 93 +++++++++++++++++++ src/qemu/qemu_monitor.h | 41 +++++++++ src/qemu/qemu_monitor_json.c | 173 +++++++++++++++++++++++++++++++++++ src/qemu/qemu_monitor_json.h | 12 +++ 4 files changed, 319 insertions(+) diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c index ab3bcc761e..b33f2eec0a 100644 --- a/src/qemu/qemu_monitor.c +++ b/src/qemu/qemu_monitor.c @@ -2651,6 +2651,99 @@ qemuMonitorGraphicsRelocate(qemuMonitorPtr mon, } +/** + * qemuMonitorAddFileHandleToSet: + * @mon: monitor object + * @fd: file descriptor to pass to qemu + * @fdset: the fdset to register this fd with, -1 to create a new fdset + * @opaque: opaque data to associated with this fd + * @info: structure that will be updated with the fd and fdset returned by qemu + * + * Attempts to register a file descriptor with qemu that can then be referenced + * via the file path /dev/fdset/$FDSETID + * Returns 0 if ok, and -1 on failure */ +int +qemuMonitorAddFileHandleToSet(qemuMonitorPtr mon, + int fd, + int fdset, + const char *opaque, + qemuMonitorAddFdInfoPtr info) +{ + VIR_DEBUG("fd=%d,fdset=%i,opaque=%s", fd, fdset, opaque); + + QEMU_CHECK_MONITOR(mon); + + if (fd < 0) { + virReportError(VIR_ERR_INVALID_ARG, "%s", + _("fd must be valid")); + return -1; + } + + return qemuMonitorJSONAddFileHandleToSet(mon, fd, fdset, opaque, info); +} + + +/** + * qemuMonitorRemoveFdset: + * @mon: monitor object + * @fdset: the fdset to remove + * + * Attempts to remove a fdset from qemu and close associated file descriptors + * Returns 0 if ok, and -1 on failure */ +int +qemuMonitorRemoveFdset(qemuMonitorPtr mon, + int fdset) +{ + VIR_DEBUG("fdset=%d", fdset); + + QEMU_CHECK_MONITOR(mon); + + if (fdset < 0) { + virReportError(VIR_ERR_INVALID_ARG, "%s", + _("fdset must be valid")); + return -1; + } + + return qemuMonitorJSONRemoveFdset(mon, fdset); +} + + +void qemuMonitorFdsetsFree(qemuMonitorFdsetsPtr fdsets) +{ + size_t i; + + for (i = 0; i < fdsets->nfdsets; i++) { + size_t j; + qemuMonitorFdsetInfoPtr set = &fdsets->fdsets[i]; + + for (j = 0; j < set->nfds; j++) + g_free(set->fds[j].opaque); + } + g_free(fdsets->fdsets); + g_free(fdsets); +} + + +/** + * qemuMonitorQueryFdsets: + * @mon: monitor object + * @fdsets: a pointer that is filled with a new qemuMonitorFdsets struct + * + * Queries qemu for the fdsets that are registered with that instance, and + * returns a structure describing those fdsets. The returned struct should be + * freed with qemuMonitorFdsetsFree(); + * + * Returns 0 if ok, and -1 on failure */ +int +qemuMonitorQueryFdsets(qemuMonitorPtr mon, + qemuMonitorFdsetsPtr *fdsets) +{ + QEMU_CHECK_MONITOR(mon); + + return qemuMonitorJSONQueryFdsets(mon, fdsets); +} + + int qemuMonitorSendFileHandle(qemuMonitorPtr mon, const char *fdname, diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h index d3f7797085..ac97aedf8a 100644 --- a/src/qemu/qemu_monitor.h +++ b/src/qemu/qemu_monitor.h @@ -880,6 +880,47 @@ int qemuMonitorGraphicsRelocate(qemuMonitorPtr mon, int tlsPort, const char *tlsSubject); +typedef struct _qemuMonitorAddFdInfo qemuMonitorAddFdInfo; +typedef qemuMonitorAddFdInfo *qemuMonitorAddFdInfoPtr; +struct _qemuMonitorAddFdInfo { + int fd; + int fdset; +}; +int +qemuMonitorAddFileHandleToSet(qemuMonitorPtr mon, + int fd, + int fdset, + const char *opaque, + qemuMonitorAddFdInfoPtr info); + +int +qemuMonitorRemoveFdset(qemuMonitorPtr mon, + int fdset); + +typedef struct _qemuMonitorFdsetFdInfo qemuMonitorFdsetFdInfo; +typedef qemuMonitorFdsetFdInfo *qemuMonitorFdsetFdInfoPtr; +struct _qemuMonitorFdsetFdInfo { + int fd; + char *opaque; +}; +typedef struct _qemuMonitorFdsetInfo qemuMonitorFdsetInfo; +typedef qemuMonitorFdsetInfo *qemuMonitorFdsetInfoPtr; +struct _qemuMonitorFdsetInfo { + int id; + qemuMonitorFdsetFdInfoPtr fds; + int nfds; +}; +typedef struct _qemuMonitorFdsets qemuMonitorFdsets; +typedef qemuMonitorFdsets *qemuMonitorFdsetsPtr; +struct _qemuMonitorFdsets { + qemuMonitorFdsetInfoPtr fdsets; + int nfdsets; +}; +void qemuMonitorFdsetsFree(qemuMonitorFdsetsPtr fdsets); +G_DEFINE_AUTOPTR_CLEANUP_FUNC(qemuMonitorFdsets, qemuMonitorFdsetsFree); +int qemuMonitorQueryFdsets(qemuMonitorPtr mon, + qemuMonitorFdsetsPtr *fdsets); + int qemuMonitorSendFileHandle(qemuMonitorPtr mon, const char *fdname, int fd); diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c index e6d2e7d4db..caa281dffa 100644 --- a/src/qemu/qemu_monitor_json.c +++ b/src/qemu/qemu_monitor_json.c @@ -3936,6 +3936,179 @@ int qemuMonitorJSONGraphicsRelocate(qemuMonitorPtr mon, } +static int +qemuAddfdInfoParse(virJSONValuePtr msg, + qemuMonitorAddFdInfoPtr fdinfo) +{ + virJSONValuePtr returnObj; + + if (!(returnObj = virJSONValueObjectGetObject(msg, "return"))) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Missing or invalid return data in add-fd response")); + return -1; + } + + if (virJSONValueObjectGetNumberInt(returnObj, "fd", &fdinfo->fd) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Missing or invalid fd in add-fd response")); + return -1; + } + + if (virJSONValueObjectGetNumberInt(returnObj, "fdset-id", &fdinfo->fdset) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Missing or invalid fdset-id in add-fd response")); + return -1; + } + + return 0; +} + + +/* if fdset is negative, qemu will create a new fdset and add the fd to that */ +int qemuMonitorJSONAddFileHandleToSet(qemuMonitorPtr mon, + int fd, + int fdset, + const char *opaque, + qemuMonitorAddFdInfoPtr fdinfo) +{ + virJSONValuePtr args = NULL; + g_autoptr(virJSONValue) reply = NULL; + g_autoptr(virJSONValue) cmd = NULL; + + if (virJSONValueObjectCreate(&args, "S:opaque", opaque, NULL) < 0) + return -1; + + if (fdset >= 0) + if (virJSONValueObjectAdd(args, "j:fdset-id", fdset, NULL) < 0) + return -1; + + if (!(cmd = qemuMonitorJSONMakeCommandInternal("add-fd", args))) + return -1; + + if (qemuMonitorJSONCommandWithFd(mon, cmd, fd, &reply) < 0) + return -1; + + if (qemuMonitorJSONCheckError(cmd, reply) < 0) + return -1; + + if (qemuAddfdInfoParse(reply, fdinfo) < 0) + return -1; + + return 0; +} + +static int +qemuMonitorJSONQueryFdsetsParse(virJSONValuePtr msg, + qemuMonitorFdsetsPtr *fdsets) +{ + virJSONValuePtr returnArray, entry; + size_t i; + g_autoptr(qemuMonitorFdsets) sets = g_new0(qemuMonitorFdsets, 1); + int ninfo; + + returnArray = virJSONValueObjectGetArray(msg, "return"); + + ninfo = virJSONValueArraySize(returnArray); + if (ninfo > 0) + sets->fdsets = g_new0(qemuMonitorFdsetInfo, ninfo); + sets->nfdsets = ninfo; + + for (i = 0; i < ninfo; i++) { + size_t j; + const char *tmp; + virJSONValuePtr fdarray; + qemuMonitorFdsetInfoPtr fdsetinfo = &sets->fdsets[i]; + + if (!(entry = virJSONValueArrayGet(returnArray, i))) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("query-fdsets return data missing fdset array element")); + return -1; + } + + if (virJSONValueObjectGetNumberInt(entry, "fdset-id", &fdsetinfo->id) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("query-fdsets reply was missing 'fdset-id'")); + return -1; + + } + + fdarray = virJSONValueObjectGetArray(entry, "fds"); + fdsetinfo->nfds = virJSONValueArraySize(fdarray); + if (fdsetinfo->nfds > 0) + fdsetinfo->fds = g_new0(qemuMonitorFdsetFdInfo, fdsetinfo->nfds); + + for (j = 0; j < fdsetinfo->nfds; j++) { + qemuMonitorFdsetFdInfoPtr fdinfo = &fdsetinfo->fds[j]; + virJSONValuePtr fdentry; + + if (!(fdentry = virJSONValueArrayGet(fdarray, j))) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("query-fdsets return data missing fd array element")); + return -1; + } + + if (virJSONValueObjectGetNumberInt(fdentry, "fd", &fdinfo->fd) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("query-fdsets return data missing 'fd'")); + return -1; + } + + /* opaque is optional and may be missing */ + tmp = virJSONValueObjectGetString(fdentry, "opaque"); + if (tmp) + fdinfo->opaque = g_strdup(tmp); + } + } + + *fdsets = g_steal_pointer(&sets); + return 0; +} + + +int qemuMonitorJSONQueryFdsets(qemuMonitorPtr mon, + qemuMonitorFdsetsPtr *fdsets) +{ + g_autoptr(virJSONValue) reply = NULL; + g_autoptr(virJSONValue) cmd = qemuMonitorJSONMakeCommand("query-fdsets", + NULL); + + if (!cmd) + return -1; + + if (qemuMonitorJSONCommand(mon, cmd, &reply) < 0) + return -1; + + if (qemuMonitorJSONCheckError(cmd, reply) < 0) + return -1; + + if (qemuMonitorJSONQueryFdsetsParse(reply, fdsets) < 0) + return -1; + + return 0; +} + + +int qemuMonitorJSONRemoveFdset(qemuMonitorPtr mon, + int fdset) +{ + g_autoptr(virJSONValue) reply = NULL; + g_autoptr(virJSONValue) cmd = qemuMonitorJSONMakeCommand("remove-fd", + "i:fdset-id", fdset, + NULL); + + if (!cmd) + return -1; + + if (qemuMonitorJSONCommand(mon, cmd, &reply) < 0) + return -1; + + if (qemuMonitorJSONCheckError(cmd, reply) < 0) + return -1; + + return 0; +} + + int qemuMonitorJSONSendFileHandle(qemuMonitorPtr mon, const char *fdname, int fd) diff --git a/src/qemu/qemu_monitor_json.h b/src/qemu/qemu_monitor_json.h index 098ab857be..2b9a42efe0 100644 --- a/src/qemu/qemu_monitor_json.h +++ b/src/qemu/qemu_monitor_json.h @@ -202,6 +202,18 @@ int qemuMonitorJSONAddPCINetwork(qemuMonitorPtr mon, int qemuMonitorJSONRemovePCIDevice(qemuMonitorPtr mon, virPCIDeviceAddress *guestAddr); +int qemuMonitorJSONAddFileHandleToSet(qemuMonitorPtr mon, + int fd, + int fdset, + const char *opaque, + qemuMonitorAddFdInfoPtr info); + +int qemuMonitorJSONRemoveFdset(qemuMonitorPtr mon, + int fdset); + +int qemuMonitorJSONQueryFdsets(qemuMonitorPtr mon, + qemuMonitorFdsetsPtr *fdsets); + int qemuMonitorJSONSendFileHandle(qemuMonitorPtr mon, const char *fdname, int fd); -- 2.26.2

On 9/24/20 5:45 PM, Jonathon Jongsma wrote: So this was moved up ahead of the call to qemuBuildHostNetStr()... ... and here you ExitMonitor prior to goto cleanup on failure... ...but  here you don't. (and should) (NB: this change does put qemuBuildHostNetStr() inside the Monitor section, but it just does a bit of string shuffling/creation, so that's not a big deal) (^^ old location of qemuDomainObjEnterMonitor()) I agree there's not much we can do here to make the situation better, but is it really going to be okay to inform the user that the device is now free, since it apparently isn't? If we go ahead and send the DEVICE_DELETED event up to the application, then it will think that the same vdpa device is now available to be re-used elsewhere. Do you have an idea what are the odds on that being true? (I don't, that's why I'm asking :-)). It may be safer to return failure, so the device is just stuck shown as in-use by this guest; that would be bad, but maybe not as bad as if it was still actually being used by this guest somehow (possible, since the fd couldn't be deleted), and a 2nd guest started using it too. (I really don't know what the consequences of any of this might be; just trying to inject my sunny disposition into the mix; truthfully I'd be willing to accept either way, just wanted to make sure it's considered). Nice attention to detail - nobody before you has bothered with a hotplug test for a network device :-) With the ExitMonitor() added where indicated, consideration of possibly failing if the fd can't be deleted, and (as with the rest of the series) as long as it's been possible to test with real hardware: Reviewed-by: Laine Stump <laine(a)redhat.com&gt;

On 9/24/20 5:45 PM, Jonathon Jongsma wrote: Can you provide an example in the commit log of what the output xml looks like for nodedev-list and nodedev-dumpxml?

On Wed, 30 Sep 2020 10:02:04 -0500 Jonathon Jongsma <jjongsma(a)redhat.com&gt; wrote: So after after a little more thinking and poking it looks like it may not be too hard to connect the sysfs path to the chardev after all. I don't have any vdpa hardware at the moment, but for vdpa_sim, the sysfs path /sys/devices/vdpa0 has a subdirectory named vhost-vdpa-0 that matches the name under /dev/ (/dev/vhost-vdpa-0). So perhaps I can use that to generate the device path. Something like this pseudo-code: for file in syspath { if file.name begins with "vhost-vdpa" { return "/dev/" + file.name; } } Are these assumptions safe? Will the file always begin with "vhost-vdpa"? Will it always match the /dev file? Jason? In that case, I can adjust the node device XML to be something like: <device> <name>vdpa_vdpa0</name> <path>/sys/devices/vdpa0</path> <parent>computer</parent> <driver> <name>vhost_vdpa</name> </driver> <capability type='vdpa'> <chardev>/dev/vhost-vdpa-0</chardev> </capability> </device> (not totally sure about the naming of the xml element).