Implement a new iommufd attribute under hostdevs' PCI subsystem driver that can be used to specify associated iommufd object when launching a qemu VM. Signed-off-by: Nathan Chen <nathanc@nvidia.com> --- docs/formatdomain.rst | 8 ++++++++ src/conf/device_conf.c | 9 +++++++++ src/conf/device_conf.h | 1 + src/conf/schemas/basictypes.rng | 5 +++++ src/qemu/qemu_command.c | 19 +++++++++++++++++++ 5 files changed, 42 insertions(+) diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index 2f1e06ba0e..61b71fdf1f 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -4836,6 +4836,7 @@ or: device; if PCI ROM loading is disabled through this attribute, attempts to tweak the loading process further using the ``bar`` or ``file`` attributes will be rejected. :since:`Since 4.3.0 (QEMU and KVM only)`. + ``address`` The ``address`` element for USB devices has a ``bus`` and ``device`` attribute to specify the USB bus and device number the device appears at on @@ -4876,6 +4877,13 @@ or: found is "problematic" in some way, the generic vfio-pci driver similarly be forced. + The ``<driver>`` element's ``iommufd`` attribute is used to specify + using the iommufd interface to propagate DMA mappings to the kernel, + instead of legacy VFIO. When the attribute is present, an iommufd + object will be created by the resulting qemu command. Libvirt will + open the /dev/iommu and VFIO device cdev, passing the associated + file descriptor numbers to the qemu command. + (Note: :since:`Since 1.0.5`, the ``name`` attribute has been described to be used to select the type of PCI device assignment ("vfio", "kvm", or "xen"), but those values have been mostly diff --git a/src/conf/device_conf.c b/src/conf/device_conf.c index c278b81652..88979ecc39 100644 --- a/src/conf/device_conf.c +++ b/src/conf/device_conf.c @@ -60,6 +60,8 @@ int virDeviceHostdevPCIDriverInfoParseXML(xmlNodePtr node, virDeviceHostdevPCIDriverInfo *driver) { + virTristateBool iommufd; + driver->iommufd = false; if (virXMLPropEnum(node, "name", virDeviceHostdevPCIDriverNameTypeFromString, VIR_XML_PROP_NONZERO, @@ -67,6 +69,10 @@ virDeviceHostdevPCIDriverInfoParseXML(xmlNodePtr node, return -1; } + if (virXMLPropTristateBool(node, "iommufd", VIR_XML_PROP_NONE, &iommufd) < 0) + return -1; + virTristateBoolToBool(iommufd, &driver->iommufd); + driver->model = virXMLPropString(node, "model"); return 0; } @@ -93,6 +99,9 @@ virDeviceHostdevPCIDriverInfoFormat(virBuffer *buf, virBufferEscapeString(&driverAttrBuf, " model='%s'", driver->model); + if (driver->iommufd) + virBufferAddLit(&driverAttrBuf, " iommufd='yes'"); + virXMLFormatElement(buf, "driver", &driverAttrBuf, NULL); return 0; } diff --git a/src/conf/device_conf.h b/src/conf/device_conf.h index e570f51824..7bdbd80b0a 100644 --- a/src/conf/device_conf.h +++ b/src/conf/device_conf.h @@ -47,6 +47,7 @@ VIR_ENUM_DECL(virDeviceHostdevPCIDriverName); struct _virDeviceHostdevPCIDriverInfo { virDeviceHostdevPCIDriverName name; char *model; + bool iommufd; }; typedef enum { diff --git a/src/conf/schemas/basictypes.rng b/src/conf/schemas/basictypes.rng index 2931e316b7..089fc0f1c2 100644 --- a/src/conf/schemas/basictypes.rng +++ b/src/conf/schemas/basictypes.rng @@ -673,6 +673,11 @@ <ref name="genericName"/> </attribute> </optional> + <optional> + <attribute name="iommufd"> + <ref name="virYesNo"/> + </attribute> + </optional> <empty/> </element> </define> diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index fc6d4ae706..c9d165dfd9 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -4808,6 +4808,7 @@ qemuBuildPCIHostdevDevProps(const virDomainDef *def, g_autofree char *host = virPCIDeviceAddressAsString(&pcisrc->addr); const char *failover_pair_id = NULL; const char *driver = NULL; + const char *iommufdId = NULL; /* 'ramfb' property must be omitted unless it's to be enabled */ bool ramfb = pcisrc->ramfb == VIR_TRISTATE_SWITCH_ON; @@ -4841,6 +4842,9 @@ qemuBuildPCIHostdevDevProps(const virDomainDef *def, teaming->persistent) failover_pair_id = teaming->persistent; + if (pcisrc->driver.iommufd) + iommufdId = "iommufd0"; + if (virJSONValueObjectAdd(&props, "s:driver", driver, "s:host", host, @@ -4849,6 +4853,7 @@ qemuBuildPCIHostdevDevProps(const virDomainDef *def, "S:failover_pair_id", failover_pair_id, "S:display", qemuOnOffAuto(pcisrc->display), "B:ramfb", ramfb, + "S:iommufd", iommufdId, NULL) < 0) return NULL; @@ -5265,6 +5270,9 @@ qemuBuildHostdevCommandLine(virCommand *cmd, virQEMUCaps *qemuCaps) { size_t i; + g_autoptr(virJSONValue) props = NULL; + int iommufd = 0; + const char * iommufdId = "iommufd0"; for (i = 0; i < def->nhostdevs; i++) { virDomainHostdevDef *hostdev = def->hostdevs[i]; @@ -5293,6 +5301,17 @@ qemuBuildHostdevCommandLine(virCommand *cmd, if (hostdev->info->type == VIR_DOMAIN_DEVICE_ADDRESS_TYPE_UNASSIGNED) continue; + if (subsys->u.pci.driver.iommufd && iommufd == 0) { + iommufd = 1; + if (qemuMonitorCreateObjectProps(&props, "iommufd", + iommufdId, + NULL) < 0) + return -1; + + if (qemuBuildObjectCommandlineFromJSON(cmd, props) < 0) + return -1; + } + if (qemuCommandAddExtDevice(cmd, hostdev->info, def, qemuCaps) < 0) return -1; -- 2.43.0