This commit introduces a new capability that reflects virtio-mem-pci device support in QEMU: QEMU_CAPS_DEVICE_VIRTIO_MEM_PCI, /* -device virtio-mem-pci */ The virtio-mem-pci device was introduced in QEMU 5.1. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; Reviewed-by: Peter Krempa <pkrempa(a)redhat.com&gt; --- src/qemu/qemu_capabilities.c | 2 ++ src/qemu/qemu_capabilities.h | 1 + tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_6.0.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_6.1.0.x86_64.xml | 1 + 6 files changed, 7 insertions(+) diff --git a/src/qemu/qemu_capabilities.c b/src/qemu/qemu_capabilities.c index d1cd8f11ac..a203aa7557 100644 --- a/src/qemu/qemu_capabilities.c +++ b/src/qemu/qemu_capabilities.c @@ -636,6 +636,7 @@ VIR_ENUM_IMPL(virQEMUCaps, /* 405 */ "confidential-guest-support", "query-display-options", + "virtio-mem-pci", ); @@ -1354,6 +1355,7 @@ struct virQEMUCapsStringFlags virQEMUCapsObjectTypes[] = { { "input-linux", QEMU_CAPS_INPUT_LINUX }, { "virtio-gpu-gl-pci", QEMU_CAPS_VIRTIO_GPU_GL_PCI }, { "virtio-vga-gl", QEMU_CAPS_VIRTIO_VGA_GL }, + { "virtio-mem-pci", QEMU_CAPS_DEVICE_VIRTIO_MEM_PCI }, }; diff --git a/src/qemu/qemu_capabilities.h b/src/qemu/qemu_capabilities.h index 7944b9170a..b2ece76e38 100644 --- a/src/qemu/qemu_capabilities.h +++ b/src/qemu/qemu_capabilities.h @@ -616,6 +616,7 @@ typedef enum { /* virQEMUCapsFlags grouping marker for syntax-check */ /* 405 */ QEMU_CAPS_MACHINE_CONFIDENTAL_GUEST_SUPPORT, /* -machine confidential-guest-support */ QEMU_CAPS_QUERY_DISPLAY_OPTIONS, /* 'query-display-options' qmp command present */ + QEMU_CAPS_DEVICE_VIRTIO_MEM_PCI, /* -device virtio-mem-pci */ 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 674d984432..268a7dcd68 100644 --- a/tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_5.1.0.x86_64.xml @@ -252,6 +252,7 @@ <flag name='rotation-rate'/> <flag name='input-linux'/> <flag name='query-display-options'/> + <flag name='virtio-mem-pci'/> <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 ec3384cab8..f924a88488 100644 --- a/tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_5.2.0.x86_64.xml @@ -253,6 +253,7 @@ <flag name='rotation-rate'/> <flag name='input-linux'/> <flag name='query-display-options'/> + <flag name='virtio-mem-pci'/> <version>5002000</version> <kvmVersion>0</kvmVersion> <microcodeVersion>43100243</microcodeVersion> diff --git a/tests/qemucapabilitiesdata/caps_6.0.0.x86_64.xml b/tests/qemucapabilitiesdata/caps_6.0.0.x86_64.xml index d6198c2479..92468f20c9 100644 --- a/tests/qemucapabilitiesdata/caps_6.0.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_6.0.0.x86_64.xml @@ -260,6 +260,7 @@ <flag name='input-linux'/> <flag name='confidential-guest-support'/> <flag name='query-display-options'/> + <flag name='virtio-mem-pci'/> <version>6000000</version> <kvmVersion>0</kvmVersion> <microcodeVersion>43100242</microcodeVersion> diff --git a/tests/qemucapabilitiesdata/caps_6.1.0.x86_64.xml b/tests/qemucapabilitiesdata/caps_6.1.0.x86_64.xml index 1937b88a4d..dfda512790 100644 --- a/tests/qemucapabilitiesdata/caps_6.1.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_6.1.0.x86_64.xml @@ -260,6 +260,7 @@ <flag name='virtio-vga-gl'/> <flag name='confidential-guest-support'/> <flag name='query-display-options'/> + <flag name='virtio-mem-pci'/> <version>6000050</version> <kvmVersion>0</kvmVersion> <microcodeVersion>43100243</microcodeVersion> -- 2.31.1

Nothing special is happening here. All important changes were done when for 'virtio-pmem' (adjusting the code to put virtio memory on PCI bus, generating alias using qemuDomainDeviceAliasIndex(). The only bit that might look suspicious is no prealloc for virtio-mem. But if you think about it, the whole purpose of this device is to change amount of memory exposed to guest on the fly. There is no point in locking the whole backend in memory. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; Reviewed-by: Peter Krempa <pkrempa(a)redhat.com&gt; --- src/qemu/qemu_alias.c | 9 +++- src/qemu/qemu_command.c | 12 +++++- ...mory-hotplug-virtio-mem.x86_64-latest.args | 41 +++++++++++++++++++ tests/qemuxml2argvtest.c | 1 + 4 files changed, 60 insertions(+), 3 deletions(-) create mode 100644 tests/qemuxml2argvdata/memory-hotplug-virtio-mem.x86_64-latest.args diff --git a/src/qemu/qemu_alias.c b/src/qemu/qemu_alias.c index 79e8953b2f..81a1e7eeed 100644 --- a/src/qemu/qemu_alias.c +++ b/src/qemu/qemu_alias.c @@ -475,8 +475,11 @@ qemuDeviceMemoryGetAliasID(virDomainDef *def, size_t i; int maxidx = 0; - /* virtio-pmem goes onto PCI bus and thus DIMM address is not valid */ - if (!oldAlias && mem->model != VIR_DOMAIN_MEMORY_MODEL_VIRTIO_PMEM) + /* virtio-pmem and virtio-mem go onto PCI bus and thus DIMM address is not + * valid */ + if (!oldAlias && + mem->model != VIR_DOMAIN_MEMORY_MODEL_VIRTIO_PMEM && + mem->model != VIR_DOMAIN_MEMORY_MODEL_VIRTIO_MEM) return mem->info.addr.dimm.slot; for (i = 0; i < def->nmems; i++) { @@ -523,6 +526,8 @@ qemuAssignDeviceMemoryAlias(virDomainDef *def, prefix = "virtiopmem"; break; case VIR_DOMAIN_MEMORY_MODEL_VIRTIO_MEM: + prefix = "virtiomem"; + break; case VIR_DOMAIN_MEMORY_MODEL_NONE: case VIR_DOMAIN_MEMORY_MODEL_LAST: default: diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index 6c5a601811..e57303fc4e 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -3083,7 +3083,9 @@ qemuBuildMemoryBackendProps(virJSONValue **backendProps, } else if (useHugepage) { if (qemuGetDomainHupageMemPath(priv->driver, def, pagesize, &memPath) < 0) return -1; - prealloc = true; + /* For virtio-mem backed by hugepages we don't need prealloc. */ + if (mem->model != VIR_DOMAIN_MEMORY_MODEL_VIRTIO_MEM) + prealloc = true; } else { /* We can have both pagesize and mem source. If that's the case, * prefer hugepages as those are more specific. */ @@ -3317,6 +3319,9 @@ qemuBuildMemoryDeviceStr(const virDomainDef *def, break; case VIR_DOMAIN_MEMORY_MODEL_VIRTIO_MEM: + device = "virtio-mem-pci"; + break; + case VIR_DOMAIN_MEMORY_MODEL_NONE: case VIR_DOMAIN_MEMORY_MODEL_LAST: default: @@ -3333,6 +3338,11 @@ qemuBuildMemoryDeviceStr(const virDomainDef *def, if (mem->labelsize) virBufferAsprintf(&buf, "label-size=%llu,", mem->labelsize * 1024); + if (mem->blocksize) { + virBufferAsprintf(&buf, "block-size=%llu,", mem->blocksize * 1024); + virBufferAsprintf(&buf, "requested-size=%llu,", mem->requestedsize * 1024); + } + if (mem->uuid) { char uuidstr[VIR_UUID_STRING_BUFLEN]; diff --git a/tests/qemuxml2argvdata/memory-hotplug-virtio-mem.x86_64-latest.args b/tests/qemuxml2argvdata/memory-hotplug-virtio-mem.x86_64-latest.args new file mode 100644 index 0000000000..16f10c14ad --- /dev/null +++ b/tests/qemuxml2argvdata/memory-hotplug-virtio-mem.x86_64-latest.args @@ -0,0 +1,41 @@ +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 \ +/usr/bin/qemu-system-i386 \ +-name guest=QEMUGuest1,debug-threads=on \ +-S \ +-object '{"qom-type":"secret","id":"masterKey0","format":"raw","file":"/tmp/lib/domain--1-QEMUGuest1/master-key.aes"}' \ +-machine pc,accel=kvm,usb=off,dump-guest-core=off \ +-cpu qemu64 \ +-m size=2095104k,slots=16,maxmem=1099511627776k \ +-overcommit mem-lock=off \ +-smp 2,sockets=2,dies=1,cores=1,threads=1 \ +-object '{"qom-type":"memory-backend-ram","id":"ram-node0","size":2145386496}' \ +-numa node,nodeid=0,cpus=0-1,memdev=ram-node0 \ +-object '{"qom-type":"memory-backend-ram","id":"memvirtiomem0","size":1073741824}' \ +-device virtio-mem-pci,node=0,block-size=2097152,requested-size=536870912,memdev=memvirtiomem0,id=virtiomem0,bus=pci.0,addr=0x2 \ +-object '{"qom-type":"memory-backend-file","id":"memvirtiomem1","mem-path":"/dev/hugepages2M/libvirt/qemu/-1-QEMUGuest1","size":2147483648,"host-nodes":[1,2,3],"policy":"bind"}' \ +-device virtio-mem-pci,node=0,block-size=2097152,requested-size=1073741824,memdev=memvirtiomem1,id=virtiomem1,bus=pci.0,addr=0x3 \ +-uuid c7a5fdbd-edaf-9455-926a-d65c16db1809 \ +-display none \ +-no-user-config \ +-nodefaults \ +-chardev socket,id=charmonitor,fd=1729,server=on,wait=off \ +-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 \ +-blockdev '{"driver":"host_device","filename":"/dev/HostVG/QEMUGuest1","node-name":"libvirt-1-storage","auto-read-only":true,"discard":"unmap"}' \ +-blockdev '{"node-name":"libvirt-1-format","read-only":false,"driver":"raw","file":"libvirt-1-storage"}' \ +-device ide-hd,bus=ide.0,unit=0,drive=libvirt-1-format,id=ide0-0-0,bootindex=1 \ +-audiodev id=audio1,driver=none \ +-device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x4 \ +-sandbox on,obsolete=deny,elevateprivileges=deny,spawn=deny,resourcecontrol=deny \ +-msg timestamp=on diff --git a/tests/qemuxml2argvtest.c b/tests/qemuxml2argvtest.c index 9df28658b9..6587cf6a92 100644 --- a/tests/qemuxml2argvtest.c +++ b/tests/qemuxml2argvtest.c @@ -3123,6 +3123,7 @@ mymain(void) QEMU_CAPS_LAST); DO_TEST_CAPS_VER("memory-hotplug-virtio-pmem", "5.2.0"); DO_TEST_CAPS_LATEST("memory-hotplug-virtio-pmem"); + DO_TEST_CAPS_LATEST("memory-hotplug-virtio-mem"); DO_TEST("machine-aeskeywrap-on-caps", QEMU_CAPS_AES_KEY_WRAP, -- 2.31.1

The virtio-mem has another property that isn't exposed yet: actual size exposed to the guest. Please note, that this is different to <requested/> because esp. on sizing the memory down guest may refuse to release some blocks. Therefore, let's have another size to report in the XML. But because of its nature, the <actual/> won't be parsed and is report only (for live XMLs). Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; --- docs/formatdomain.rst | 7 +++++++ docs/schemas/domaincommon.rng | 5 +++++ src/conf/domain_conf.c | 9 +++++++-- src/conf/domain_conf.h | 3 +++ 4 files changed, 22 insertions(+), 2 deletions(-) diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index 967d5bbb91..01e5a3fe03 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -7773,6 +7773,7 @@ Example: usage of the memory devices <node>0</node> <block unit='KiB'>2048</block> <requested unit='KiB'>1048576</requested> + <actual unit='KiB'>524288</requested> </target> </memory> </devices> @@ -7888,6 +7889,12 @@ Example: usage of the memory devices The total size exposed to the guest. Must respect ``block`` granularity and be smaller than or equal to ``size``. + ``actual`` + Active XML for ``virtio-mem`` model may contain ``actual`` element that + reflects the actual size of the corresponding virtio memory device. The + element is formatted into live XML and never parsed, i.e. it is + output-only element. + :anchor:`<a id="elementsIommu"/>` IOMMU devices diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index 439dd893ff..b832dce19b 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -6649,6 +6649,11 @@ <ref name="scaledInteger"/> </element> </optional> + <optional> + <element name="actual"> + <ref name="scaledInteger"/> + </element> + </optional> <optional> <element name="label"> <element name="size"> diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 76344b592d..1ef70e8a80 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -25870,7 +25870,8 @@ virDomainMemorySourceDefFormat(virBuffer *buf, static void virDomainMemoryTargetDefFormat(virBuffer *buf, - virDomainMemoryDef *def) + virDomainMemoryDef *def, + unsigned int flags) { g_auto(virBuffer) childBuf = VIR_BUFFER_INIT_CHILD(buf); @@ -25892,6 +25893,10 @@ virDomainMemoryTargetDefFormat(virBuffer *buf, virBufferAsprintf(&childBuf, "<requested unit='KiB'>%llu</requested>\n", def->requestedsize); + if (!(flags & VIR_DOMAIN_DEF_FORMAT_INACTIVE)) { + virBufferAsprintf(&childBuf, "<actual unit='KiB'>%llu</actual>\n", + def->actualsize); + } } virXMLFormatElement(buf, "target", NULL, &childBuf); @@ -25924,7 +25929,7 @@ virDomainMemoryDefFormat(virBuffer *buf, if (virDomainMemorySourceDefFormat(buf, def) < 0) return -1; - virDomainMemoryTargetDefFormat(buf, def); + virDomainMemoryTargetDefFormat(buf, def, flags); virDomainDeviceInfoFormat(buf, &def->info, flags); diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index 0c43a6ae64..b57eba655d 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -2482,6 +2482,9 @@ struct _virDomainMemoryDef { unsigned long long labelsize; /* kibibytes; valid only for NVDIMM */ unsigned long long blocksize; /* kibibytes; valid only for VIRTIO_MEM */ unsigned long long requestedsize; /* kibibytes; valid only for VIRTIO_MEM */ + unsigned long long actualsize; /* kibibytes, valid for VIRTIO_MEM and + active domain only, only to report never + parse */ bool readonly; /* valid only for NVDIMM */ /* required for QEMU NVDIMM ppc64 support */ -- 2.31.1

As advertised in previous commit, this event is delivered to us when virtio-mem module changes the allocation inside the guest. It comes with one attribute - size - which holds the new size of the virtio-mem (well, allocated size), in bytes. Mind you, this is not necessarily the same number as 'requested size'. It almost certainly will be when sizing the memory up, but it might not be when sizing the memory down - the guest kernel might be unable to free some blocks. This actual size is reported in the domain XML as an output element only. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; --- examples/c/misc/event-test.c | 17 ++++++ include/libvirt/libvirt-domain.h | 23 ++++++++ src/conf/domain_event.c | 84 +++++++++++++++++++++++++++++ src/conf/domain_event.h | 10 ++++ src/libvirt_private.syms | 2 + src/qemu/qemu_domain.c | 3 ++ src/qemu/qemu_domain.h | 1 + src/qemu/qemu_driver.c | 37 +++++++++++++ src/qemu/qemu_monitor.c | 24 +++++++++ src/qemu/qemu_monitor.h | 20 +++++++ src/qemu/qemu_monitor_json.c | 24 +++++++++ src/qemu/qemu_process.c | 42 +++++++++++++++ src/remote/remote_daemon_dispatch.c | 30 +++++++++++ src/remote/remote_driver.c | 32 +++++++++++ src/remote/remote_protocol.x | 14 ++++- src/remote_protocol-structs | 7 +++ tools/virsh-domain.c | 20 +++++++ 17 files changed, 389 insertions(+), 1 deletion(-) diff --git a/examples/c/misc/event-test.c b/examples/c/misc/event-test.c index 10c707e66b..1eec76c79d 100644 --- a/examples/c/misc/event-test.c +++ b/examples/c/misc/event-test.c @@ -982,6 +982,22 @@ myDomainEventMemoryFailureCallback(virConnectPtr conn G_GNUC_UNUSED, } +static int +myDomainEventMemoryDeviceSizeChangeCallback(virConnectPtr conn G_GNUC_UNUSED, + virDomainPtr dom, + const char *alias, + unsigned long long size, + void *opaque G_GNUC_UNUSED) +{ + /* Casts to uint64_t to work around mingw not knowing %lld */ + printf("%s EVENT: Domain %s(%d) memory device size change: " + "alias: '%s' new size %" PRIu64 "'\n", + __func__, virDomainGetName(dom), virDomainGetID(dom), + alias, (uint64_t)size); + return 0; +} + + static int myDomainEventMigrationIterationCallback(virConnectPtr conn G_GNUC_UNUSED, virDomainPtr dom, @@ -1113,6 +1129,7 @@ struct domainEventData domainEvents[] = { DOMAIN_EVENT(VIR_DOMAIN_EVENT_ID_METADATA_CHANGE, myDomainEventMetadataChangeCallback), DOMAIN_EVENT(VIR_DOMAIN_EVENT_ID_BLOCK_THRESHOLD, myDomainEventBlockThresholdCallback), DOMAIN_EVENT(VIR_DOMAIN_EVENT_ID_MEMORY_FAILURE, myDomainEventMemoryFailureCallback), + DOMAIN_EVENT(VIR_DOMAIN_EVENT_ID_MEMORY_DEVICE_SIZE_CHANGE, myDomainEventMemoryDeviceSizeChangeCallback), }; struct storagePoolEventData { diff --git a/include/libvirt/libvirt-domain.h b/include/libvirt/libvirt-domain.h index 7ef8ac51e5..534063d15b 100644 --- a/include/libvirt/libvirt-domain.h +++ b/include/libvirt/libvirt-domain.h @@ -4654,6 +4654,28 @@ typedef void (*virConnectDomainEventMemoryFailureCallback)(virConnectPtr conn, unsigned int flags, void *opaque); +/** + * virConnectDomainEventMemoryDeviceSizeChangeCallback: + * @conn: connection object + * @dom: domain on which the event occurred + * @alias: memory device alias + * @size: new actual size of memory device (in KiB) + * @opaque: application specified data + * + * The callback occurs when the guest acknowledges request to change size of + * memory device (so far only virtio-mem model supports this). The @size then + * reflects the new amount of guest visible memory (in kibibytes). + * + * The callback signature to use when registering for an event of type + * VIR_DOMAIN_EVENT_ID_MEMORY_DEVICE_SIZE_CHANGE with + * virConnectDomainEventRegisterAny(). + */ +typedef void (*virConnectDomainEventMemoryDeviceSizeChangeCallback)(virConnectPtr conn, + virDomainPtr dom, + const char *alias, + unsigned long long size, + void *opaque); + /** * VIR_DOMAIN_EVENT_CALLBACK: @@ -4698,6 +4720,7 @@ typedef enum { VIR_DOMAIN_EVENT_ID_METADATA_CHANGE = 23, /* virConnectDomainEventMetadataChangeCallback */ VIR_DOMAIN_EVENT_ID_BLOCK_THRESHOLD = 24, /* virConnectDomainEventBlockThresholdCallback */ VIR_DOMAIN_EVENT_ID_MEMORY_FAILURE = 25, /* virConnectDomainEventMemoryFailureCallback */ + VIR_DOMAIN_EVENT_ID_MEMORY_DEVICE_SIZE_CHANGE = 26, /* virConnectDomainEventMemoryDeviceSizeChangeCallback */ # ifdef VIR_ENUM_SENTINELS VIR_DOMAIN_EVENT_ID_LAST diff --git a/src/conf/domain_event.c b/src/conf/domain_event.c index 15a3baedf7..18539e348b 100644 --- a/src/conf/domain_event.c +++ b/src/conf/domain_event.c @@ -58,6 +58,7 @@ static virClass *virDomainEventDeviceRemovalFailedClass; static virClass *virDomainEventMetadataChangeClass; static virClass *virDomainEventBlockThresholdClass; static virClass *virDomainEventMemoryFailureClass; +static virClass *virDomainEventMemoryDeviceSizeChangeClass; static void virDomainEventDispose(void *obj); static void virDomainEventLifecycleDispose(void *obj); @@ -81,6 +82,7 @@ static void virDomainEventDeviceRemovalFailedDispose(void *obj); static void virDomainEventMetadataChangeDispose(void *obj); static void virDomainEventBlockThresholdDispose(void *obj); static void virDomainEventMemoryFailureDispose(void *obj); +static void virDomainEventMemoryDeviceSizeChangeDispose(void *obj); static void virDomainEventDispatchDefaultFunc(virConnectPtr conn, @@ -277,6 +279,15 @@ struct _virDomainEventMemoryFailure { }; typedef struct _virDomainEventMemoryFailure virDomainEventMemoryFailure; +struct _virDomainEventMemoryDeviceSizeChange { + virDomainEvent parent; + + char *alias; + unsigned long long size; +}; +typedef struct _virDomainEventMemoryDeviceSizeChange virDomainEventMemoryDeviceSizeChange; +typedef virDomainEventMemoryDeviceSizeChange *virDomainEventMemoryDeviceSizeChangePtr; + static int virDomainEventsOnceInit(void) { @@ -324,6 +335,8 @@ virDomainEventsOnceInit(void) return -1; if (!VIR_CLASS_NEW(virDomainEventMemoryFailure, virDomainEventClass)) return -1; + if (!VIR_CLASS_NEW(virDomainEventMemoryDeviceSizeChange, virDomainEventClass)) + return -1; return 0; } @@ -540,6 +553,14 @@ virDomainEventMemoryFailureDispose(void *obj) VIR_DEBUG("obj=%p", event); } +static void +virDomainEventMemoryDeviceSizeChangeDispose(void *obj) +{ + virDomainEventMemoryDeviceSizeChangePtr event = obj; + VIR_DEBUG("obj=%p", event); + + g_free(event->alias); +} static void * virDomainEventNew(virClass *klass, @@ -1664,6 +1685,57 @@ virDomainEventMemoryFailureNewFromDom(virDomainPtr dom, recipient, action, flags); } + +static virObjectEvent * +virDomainEventMemoryDeviceSizeChangeNew(int id, + const char *name, + unsigned char *uuid, + const char *alias, + unsigned long long size) +{ + virDomainEventMemoryDeviceSizeChangePtr ev; + + if (virDomainEventsInitialize() < 0) + return NULL; + + if (!(ev = virDomainEventNew(virDomainEventMemoryDeviceSizeChangeClass, + VIR_DOMAIN_EVENT_ID_MEMORY_DEVICE_SIZE_CHANGE, + id, name, uuid))) + return NULL; + + ev->alias = g_strdup(alias); + ev->size = size; + + return (virObjectEvent *)ev; +} + + +virObjectEvent * +virDomainEventMemoryDeviceSizeChangeNewFromObj(virDomainObj *obj, + const char *alias, + unsigned long long size) +{ + return virDomainEventMemoryDeviceSizeChangeNew(obj->def->id, + obj->def->name, + obj->def->uuid, + alias, + size); +} + + +virObjectEvent * +virDomainEventMemoryDeviceSizeChangeNewFromDom(virDomainPtr dom, + const char *alias, + unsigned long long size) +{ + return virDomainEventMemoryDeviceSizeChangeNew(dom->id, + dom->name, + dom->uuid, + alias, + size); +} + + static void virDomainEventDispatchDefaultFunc(virConnectPtr conn, virObjectEvent *event, @@ -1960,6 +2032,18 @@ virDomainEventDispatchDefaultFunc(virConnectPtr conn, goto cleanup; } + case VIR_DOMAIN_EVENT_ID_MEMORY_DEVICE_SIZE_CHANGE: + { + virDomainEventMemoryDeviceSizeChangePtr memoryDeviceSizeChangeEvent; + + memoryDeviceSizeChangeEvent = (virDomainEventMemoryDeviceSizeChangePtr)event; + ((virConnectDomainEventMemoryDeviceSizeChangeCallback)cb)(conn, dom, + memoryDeviceSizeChangeEvent->alias, + memoryDeviceSizeChangeEvent->size, + cbopaque); + goto cleanup; + } + case VIR_DOMAIN_EVENT_ID_LAST: break; } diff --git a/src/conf/domain_event.h b/src/conf/domain_event.h index 2a59e613cd..4a9f6b988b 100644 --- a/src/conf/domain_event.h +++ b/src/conf/domain_event.h @@ -267,6 +267,16 @@ virDomainEventMemoryFailureNewFromDom(virDomainPtr dom, int action, unsigned int flags); +virObjectEvent * +virDomainEventMemoryDeviceSizeChangeNewFromObj(virDomainObj *obj, + const char *alias, + unsigned long long size); + +virObjectEvent * +virDomainEventMemoryDeviceSizeChangeNewFromDom(virDomainPtr dom, + const char *alias, + unsigned long long size); + int virDomainEventStateRegister(virConnectPtr conn, virObjectEventState *state, diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms index 0721e13143..e25866c60b 100644 --- a/src/libvirt_private.syms +++ b/src/libvirt_private.syms @@ -719,6 +719,8 @@ virDomainEventLifecycleNew; virDomainEventLifecycleNewFromDef; virDomainEventLifecycleNewFromDom; virDomainEventLifecycleNewFromObj; +virDomainEventMemoryDeviceSizeChangeNewFromDom; +virDomainEventMemoryDeviceSizeChangeNewFromObj; virDomainEventMemoryFailureNewFromDom; virDomainEventMemoryFailureNewFromObj; virDomainEventMetadataChangeNewFromDom; diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index d4ad29fac4..91a598c208 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -11007,6 +11007,9 @@ qemuProcessEventFree(struct qemuProcessEvent *event) case QEMU_PROCESS_EVENT_JOB_STATUS_CHANGE: virObjectUnref(event->data); break; + case QEMU_PROCESS_EVENT_MEMORY_DEVICE_SIZE_CHANGE: + qemuMonitorMemoryDeviceSizeChangeFree(event->data); + break; case QEMU_PROCESS_EVENT_PR_DISCONNECT: case QEMU_PROCESS_EVENT_LAST: break; diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h index acf6ca5ab6..282ae345d5 100644 --- a/src/qemu/qemu_domain.h +++ b/src/qemu/qemu_domain.h @@ -430,6 +430,7 @@ typedef enum { QEMU_PROCESS_EVENT_PR_DISCONNECT, QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED, QEMU_PROCESS_EVENT_GUEST_CRASHLOADED, + QEMU_PROCESS_EVENT_MEMORY_DEVICE_SIZE_CHANGE, QEMU_PROCESS_EVENT_LAST } qemuProcessEventType; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index a638c67f1e..996f97b526 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4300,6 +4300,40 @@ processGuestCrashloadedEvent(virQEMUDriver *driver, } +static void +processMemoryDeviceSizeChange(virQEMUDriver *driver, + virDomainObj *vm, + qemuMonitorMemoryDeviceSizeChange *info) +{ + virDomainMemoryDef *mem = NULL; + virObjectEvent *event = NULL; + + if (qemuDomainObjBeginJob(driver, vm, QEMU_JOB_MODIFY) < 0) + return; + + if (!virDomainObjIsActive(vm)) { + VIR_DEBUG("Domain is not running"); + goto endjob; + } + + mem = virDomainMemoryFindByDeviceAlias(vm->def, info->devAlias); + if (!mem) { + VIR_DEBUG("Memory device '%s' not found", info->devAlias); + goto endjob; + } + + mem->actualsize = VIR_DIV_UP(info->size, 1024); + + event = virDomainEventMemoryDeviceSizeChangeNewFromObj(vm, + info->devAlias, + mem->actualsize); + + endjob: + qemuDomainObjEndJob(driver, vm); + virObjectEventStateQueue(driver->domainEventState, event); +} + + static void qemuProcessEventHandler(void *data, void *opaque) { struct qemuProcessEvent *processEvent = data; @@ -4349,6 +4383,9 @@ static void qemuProcessEventHandler(void *data, void *opaque) case QEMU_PROCESS_EVENT_GUEST_CRASHLOADED: processGuestCrashloadedEvent(driver, vm); break; + case QEMU_PROCESS_EVENT_MEMORY_DEVICE_SIZE_CHANGE: + processMemoryDeviceSizeChange(driver, vm, processEvent->data); + break; case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c index be04684585..aeaa7ee975 100644 --- a/src/qemu/qemu_monitor.c +++ b/src/qemu/qemu_monitor.c @@ -1446,6 +1446,20 @@ qemuMonitorEmitSpiceMigrated(qemuMonitor *mon) } +int +qemuMonitorEmitMemoryDeviceSizeChange(qemuMonitor *mon, + const char *devAlias, + unsigned long long size) +{ + int ret = -1; + VIR_DEBUG("mon=%p, devAlias='%s', size=%llu", mon, devAlias, size); + + QEMU_MONITOR_CALLBACK(mon, ret, domainMemoryDeviceSizeChange, mon->vm, devAlias, size); + + return ret; +} + + int qemuMonitorEmitMemoryFailure(qemuMonitor *mon, qemuMonitorEventMemoryFailure *mfp) @@ -4393,6 +4407,16 @@ qemuMonitorEventRdmaGidStatusFree(qemuMonitorRdmaGidStatus *info) } +void +qemuMonitorMemoryDeviceSizeChangeFree(qemuMonitorMemoryDeviceSizeChangePtr info) +{ + if (!info) + return; + + g_free(info->devAlias); +} + + int qemuMonitorSetWatchdogAction(qemuMonitor *mon, const char *action) diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h index b5de5711e0..1c69a86af0 100644 --- a/src/qemu/qemu_monitor.h +++ b/src/qemu/qemu_monitor.h @@ -101,6 +101,14 @@ struct _qemuMonitorRdmaGidStatus { }; +typedef struct _qemuMonitorMemoryDeviceSizeChange qemuMonitorMemoryDeviceSizeChange; +typedef qemuMonitorMemoryDeviceSizeChange *qemuMonitorMemoryDeviceSizeChangePtr; +struct _qemuMonitorMemoryDeviceSizeChange { + char *devAlias; + unsigned long long size; +}; + + typedef enum { QEMU_MONITOR_JOB_TYPE_UNKNOWN, /* internal value, not exposed by qemu */ QEMU_MONITOR_JOB_TYPE_COMMIT, @@ -145,6 +153,7 @@ struct _qemuMonitorJobInfo { char *qemuMonitorGuestPanicEventInfoFormatMsg(qemuMonitorEventPanicInfo *info); void qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfo *info); void qemuMonitorEventRdmaGidStatusFree(qemuMonitorRdmaGidStatus *info); +void qemuMonitorMemoryDeviceSizeChangeFree(qemuMonitorMemoryDeviceSizeChange *info); typedef void (*qemuMonitorDestroyCallback)(qemuMonitor *mon, virDomainObj *vm, @@ -364,6 +373,12 @@ typedef int (*qemuMonitorDomainMemoryFailureCallback)(qemuMonitor *mon, qemuMonitorEventMemoryFailure *mfp, void *opaque); +typedef int (*qemuMonitorDomainMemoryDeviceSizeChange)(qemuMonitor *mon, + virDomainObj *vm, + const char *alias, + unsigned long long size, + void *opaque); + typedef struct _qemuMonitorCallbacks qemuMonitorCallbacks; struct _qemuMonitorCallbacks { qemuMonitorDestroyCallback destroy; @@ -400,6 +415,7 @@ struct _qemuMonitorCallbacks { qemuMonitorDomainRdmaGidStatusChangedCallback domainRdmaGidStatusChanged; qemuMonitorDomainGuestCrashloadedCallback domainGuestCrashloaded; qemuMonitorDomainMemoryFailureCallback domainMemoryFailure; + qemuMonitorDomainMemoryDeviceSizeChange domainMemoryDeviceSizeChange; }; qemuMonitor *qemuMonitorOpen(virDomainObj *vm, @@ -496,6 +512,10 @@ int qemuMonitorEmitSerialChange(qemuMonitor *mon, bool connected); int qemuMonitorEmitSpiceMigrated(qemuMonitor *mon); +int qemuMonitorEmitMemoryDeviceSizeChange(qemuMonitor *mon, + const char *devAlias, + unsigned long long size); + int qemuMonitorEmitMemoryFailure(qemuMonitor *mon, qemuMonitorEventMemoryFailure *mfp); diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c index d3db88a389..57b78cd686 100644 --- a/src/qemu/qemu_monitor_json.c +++ b/src/qemu/qemu_monitor_json.c @@ -113,6 +113,7 @@ static void qemuMonitorJSONHandleDumpCompleted(qemuMonitor *mon, virJSONValue *d static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitor *mon, virJSONValue *data); static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitor *mon, virJSONValue *data); static void qemuMonitorJSONHandleMemoryFailure(qemuMonitor *mon, virJSONValue *data); +static void qemuMonitorJSONHandleMemoryDeviceSizeChange(qemuMonitor *mon, virJSONValue *data); typedef struct { const char *type; @@ -133,6 +134,7 @@ static qemuEventHandler eventHandlers[] = { { "GUEST_CRASHLOADED", qemuMonitorJSONHandleGuestCrashloaded, }, { "GUEST_PANICKED", qemuMonitorJSONHandleGuestPanic, }, { "JOB_STATUS_CHANGE", qemuMonitorJSONHandleJobStatusChange, }, + { "MEMORY_DEVICE_SIZE_CHANGE", qemuMonitorJSONHandleMemoryDeviceSizeChange, }, { "MEMORY_FAILURE", qemuMonitorJSONHandleMemoryFailure, }, { "MIGRATION", qemuMonitorJSONHandleMigrationStatus, }, { "MIGRATION_PASS", qemuMonitorJSONHandleMigrationPass, }, @@ -1320,6 +1322,28 @@ qemuMonitorJSONHandleSpiceMigrated(qemuMonitor *mon, } +static void +qemuMonitorJSONHandleMemoryDeviceSizeChange(qemuMonitor *mon, + virJSONValue *data) +{ + const char *name; + unsigned long long size; + + if (!(name = virJSONValueObjectGetString(data, "id"))) { + VIR_WARN("missing device alias in MEMORY_DEVICE_SIZE_CHANGE event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "size", &size) < 0) { + VIR_WARN("missing new size for '%s' in MEMORY_DEVICE_SIZE_CHANGE event", name); + return; + } + + + qemuMonitorEmitMemoryDeviceSizeChange(mon, name, size); +} + + static void qemuMonitorJSONHandleMemoryFailure(qemuMonitor *mon, virJSONValue *data) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 62208048b0..78e5a65d5f 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -1919,6 +1919,47 @@ qemuProcessHandleMemoryFailure(qemuMonitor *mon G_GNUC_UNUSED, } +static int +qemuProcessHandleMemoryDeviceSizeChange(qemuMonitor *mon G_GNUC_UNUSED, + virDomainObj *vm, + const char *devAlias, + unsigned long long size, + void *opaque) +{ + virQEMUDriver *driver = opaque; + struct qemuProcessEvent *processEvent = NULL; + qemuMonitorMemoryDeviceSizeChange *info = NULL; + int ret = -1; + + virObjectLock(vm); + + VIR_DEBUG("Memory device '%s' changed size to '%llu' in domain '%s'", + devAlias, size, vm->def->name); + + info = g_new0(qemuMonitorMemoryDeviceSizeChange, 1); + info->devAlias = g_strdup(devAlias); + info->size = size; + + processEvent = g_new0(struct qemuProcessEvent, 1); + processEvent->eventType = QEMU_PROCESS_EVENT_MEMORY_DEVICE_SIZE_CHANGE; + processEvent->vm = virObjectRef(vm); + processEvent->data = g_steal_pointer(&info); + + if (virThreadPoolSendJob(driver->workerPool, 0, processEvent) < 0) { + qemuProcessEventFree(processEvent); + virObjectUnref(vm); + goto cleanup; + } + + processEvent = NULL; + ret = 0; + cleanup: + qemuProcessEventFree(processEvent); + virObjectUnlock(vm); + return ret; +} + + static qemuMonitorCallbacks monitorCallbacks = { .eofNotify = qemuProcessHandleMonitorEOF, .errorNotify = qemuProcessHandleMonitorError, @@ -1952,6 +1993,7 @@ static qemuMonitorCallbacks monitorCallbacks = { .domainRdmaGidStatusChanged = qemuProcessHandleRdmaGidStatusChanged, .domainGuestCrashloaded = qemuProcessHandleGuestCrashloaded, .domainMemoryFailure = qemuProcessHandleMemoryFailure, + .domainMemoryDeviceSizeChange = qemuProcessHandleMemoryDeviceSizeChange, }; static void diff --git a/src/remote/remote_daemon_dispatch.c b/src/remote/remote_daemon_dispatch.c index 65aa20f7d1..ff81ecfa79 100644 --- a/src/remote/remote_daemon_dispatch.c +++ b/src/remote/remote_daemon_dispatch.c @@ -1334,6 +1334,35 @@ remoteRelayDomainEventMemoryFailure(virConnectPtr conn, } +static int +remoteRelayDomainEventMemoryDeviceSizeChange(virConnectPtr conn, + virDomainPtr dom, + const char *alias, + unsigned long long size, + void *opaque) +{ + daemonClientEventCallback *callback = opaque; + remote_domain_event_memory_device_size_change_msg data; + + if (callback->callbackID < 0 || + !remoteRelayDomainEventCheckACL(callback->client, conn, dom)) + return -1; + + /* build return data */ + memset(&data, 0, sizeof(data)); + data.callbackID = callback->callbackID; + data.alias = g_strdup(alias); + data.size = size; + make_nonnull_domain(&data.dom, dom); + + remoteDispatchObjectEventSend(callback->client, remoteProgram, + REMOTE_PROC_DOMAIN_EVENT_MEMORY_DEVICE_SIZE_CHANGE, + (xdrproc_t)xdr_remote_domain_event_memory_device_size_change_msg, + &data); + return 0; +} + + static virConnectDomainEventGenericCallback domainEventCallbacks[] = { VIR_DOMAIN_EVENT_CALLBACK(remoteRelayDomainEventLifecycle), VIR_DOMAIN_EVENT_CALLBACK(remoteRelayDomainEventReboot), @@ -1361,6 +1390,7 @@ static virConnectDomainEventGenericCallback domainEventCallbacks[] = { VIR_DOMAIN_EVENT_CALLBACK(remoteRelayDomainEventMetadataChange), VIR_DOMAIN_EVENT_CALLBACK(remoteRelayDomainEventBlockThreshold), VIR_DOMAIN_EVENT_CALLBACK(remoteRelayDomainEventMemoryFailure), + VIR_DOMAIN_EVENT_CALLBACK(remoteRelayDomainEventMemoryDeviceSizeChange), }; G_STATIC_ASSERT(G_N_ELEMENTS(domainEventCallbacks) == VIR_DOMAIN_EVENT_ID_LAST); diff --git a/src/remote/remote_driver.c b/src/remote/remote_driver.c index c03c68ec30..1f94be6cbc 100644 --- a/src/remote/remote_driver.c +++ b/src/remote/remote_driver.c @@ -410,6 +410,10 @@ remoteDomainBuildEventMemoryFailure(virNetClientProgram *prog, void *evdata, void *opaque); static void +remoteDomainBuildEventMemoryDeviceSizeChange(virNetClientProgram *prog, + virNetClient *client, + void *evdata, void *opaque); +static void remoteConnectNotifyEventConnectionClosed(virNetClientProgram *prog G_GNUC_UNUSED, virNetClient *client G_GNUC_UNUSED, void *evdata, void *opaque); @@ -624,6 +628,10 @@ static virNetClientProgramEvent remoteEvents[] = { remoteDomainBuildEventMemoryFailure, sizeof(remote_domain_event_memory_failure_msg), (xdrproc_t)xdr_remote_domain_event_memory_failure_msg }, + { REMOTE_PROC_DOMAIN_EVENT_MEMORY_DEVICE_SIZE_CHANGE, + remoteDomainBuildEventMemoryDeviceSizeChange, + sizeof(remote_domain_event_memory_device_size_change_msg), + (xdrproc_t)xdr_remote_domain_event_memory_device_size_change_msg }, }; static void @@ -5436,6 +5444,30 @@ remoteDomainBuildEventMemoryFailure(virNetClientProgram *prog G_GNUC_UNUSED, } +static void +remoteDomainBuildEventMemoryDeviceSizeChange(virNetClientProgram *prog G_GNUC_UNUSED, + virNetClient *client G_GNUC_UNUSED, + void *evdata, void *opaque) +{ + virConnectPtr conn = opaque; + remote_domain_event_memory_device_size_change_msg *msg = evdata; + struct private_data *priv = conn->privateData; + virDomainPtr dom; + virObjectEvent *event = NULL; + + if (!(dom = get_nonnull_domain(conn, msg->dom))) + return; + + event = virDomainEventMemoryDeviceSizeChangeNewFromDom(dom, + msg->alias, + msg->size); + + virObjectUnref(dom); + + virObjectEventStateQueueRemote(priv->eventState, event, msg->callbackID); +} + + static int remoteStreamSend(virStreamPtr st, const char *data, diff --git a/src/remote/remote_protocol.x b/src/remote/remote_protocol.x index de69704b68..a45bdaa7e8 100644 --- a/src/remote/remote_protocol.x +++ b/src/remote/remote_protocol.x @@ -3837,6 +3837,13 @@ struct remote_domain_start_dirty_rate_calc_args { }; +struct remote_domain_event_memory_device_size_change_msg { + int callbackID; + remote_nonnull_domain dom; + remote_nonnull_string alias; + unsigned hyper size; +}; + /*----- Protocol. -----*/ /* Define the program number, protocol version and procedure numbers here. */ @@ -6784,6 +6791,11 @@ enum remote_procedure { * @priority: high * @acl: node_device:start */ - REMOTE_PROC_NODE_DEVICE_CREATE = 430 + REMOTE_PROC_NODE_DEVICE_CREATE = 430, + /** + * @generate: both + * @acl: none + */ + REMOTE_PROC_DOMAIN_EVENT_MEMORY_DEVICE_SIZE_CHANGE = 431 }; diff --git a/src/remote_protocol-structs b/src/remote_protocol-structs index 6b46328adc..7286c06ae8 100644 --- a/src/remote_protocol-structs +++ b/src/remote_protocol-structs @@ -3192,6 +3192,12 @@ struct remote_domain_start_dirty_rate_calc_args { int seconds; u_int flags; }; +struct remote_domain_event_memory_device_size_change_msg { + int callbackID; + remote_nonnull_domain dom; + remote_nonnull_string alias; + uint64_t size; +}; enum remote_procedure { REMOTE_PROC_CONNECT_OPEN = 1, REMOTE_PROC_CONNECT_CLOSE = 2, @@ -3623,4 +3629,5 @@ enum remote_procedure { REMOTE_PROC_NODE_DEVICE_DEFINE_XML = 428, REMOTE_PROC_NODE_DEVICE_UNDEFINE = 429, REMOTE_PROC_NODE_DEVICE_CREATE = 430, + REMOTE_PROC_DOMAIN_EVENT_MEMORY_DEVICE_SIZE_CHANGE = 431, }; diff --git a/tools/virsh-domain.c b/tools/virsh-domain.c index f2a5fb03a4..b69eb3e346 100644 --- a/tools/virsh-domain.c +++ b/tools/virsh-domain.c @@ -13464,6 +13464,24 @@ virshEventMemoryFailurePrint(virConnectPtr conn G_GNUC_UNUSED, } +static void +virshEventMemoryDeviceSizeChangePrint(virConnectPtr conn G_GNUC_UNUSED, + virDomainPtr dom, + const char *alias, + unsigned long long size, + void *opaque) +{ + g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER; + + virBufferAsprintf(&buf, + _("event 'memory-device-size-change' for domain '%s':\n" + "alias: %s\nsize: %llu\n"), + virDomainGetName(dom), alias, size); + + virshEventPrint(opaque, &buf); +} + + virshDomainEventCallback virshDomainEventCallbacks[] = { { "lifecycle", VIR_DOMAIN_EVENT_CALLBACK(virshEventLifecyclePrint), }, @@ -13515,6 +13533,8 @@ virshDomainEventCallback virshDomainEventCallbacks[] = { VIR_DOMAIN_EVENT_CALLBACK(virshEventBlockThresholdPrint), }, { "memory-failure", VIR_DOMAIN_EVENT_CALLBACK(virshEventMemoryFailurePrint), }, + { "memory-device-size-change", + VIR_DOMAIN_EVENT_CALLBACK(virshEventMemoryDeviceSizeChangePrint), }, }; G_STATIC_ASSERT(VIR_DOMAIN_EVENT_ID_LAST == G_N_ELEMENTS(virshDomainEventCallbacks)); -- 2.31.1

Reporting how much memory is exposed to the guest happens under <currentMemory/> which is taken from def->mem.cur_balloon. The reported amount should account for both balloon size and the sum of @actualsize of all virtio-mems. For instance, if domain has 4GiB via balloon and additional 2GiB via virtio-mem, then the domain XML should report 6GiB. The same applies for domain statistics. The way to achieve this is to account for either balloon or virtio-mem when the size of the other is changed, e.g. on balloon change we have to add all @actualsize (for non virtio-mem these will be zero, so the check for memory model is needless, but makes it more obvious what's happening), and vice versa. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; --- src/qemu/qemu_driver.c | 9 +++++++++ src/qemu/qemu_process.c | 25 +++++++++++++++++++++++++ 2 files changed, 34 insertions(+) diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 996f97b526..735e383da6 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4307,6 +4307,7 @@ processMemoryDeviceSizeChange(virQEMUDriver *driver, { virDomainMemoryDef *mem = NULL; virObjectEvent *event = NULL; + unsigned long long balloon; if (qemuDomainObjBeginJob(driver, vm, QEMU_JOB_MODIFY) < 0) return; @@ -4322,7 +4323,15 @@ processMemoryDeviceSizeChange(virQEMUDriver *driver, goto endjob; } + /* If this looks weird it's because it is. The balloon size + * as reported by QEMU does not include any of @actualsize. + * It really contains just the balloon size. But in domain + * definition we want to report also sum of @actualsize. Do + * a bit of math to fix the domain definition. */ + balloon = vm->def->mem.cur_balloon - mem->actualsize; mem->actualsize = VIR_DIV_UP(info->size, 1024); + balloon += mem->actualsize; + vm->def->mem.cur_balloon = balloon; event = virDomainEventMemoryDeviceSizeChangeNewFromObj(vm, info->devAlias, diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 8e82043f43..06d46b31dc 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -1232,10 +1232,22 @@ qemuProcessHandleBalloonChange(qemuMonitor *mon G_GNUC_UNUSED, virQEMUDriver *driver = opaque; virObjectEvent *event = NULL; g_autoptr(virQEMUDriverConfig) cfg = virQEMUDriverGetConfig(driver); + size_t i; virObjectLock(vm); event = virDomainEventBalloonChangeNewFromObj(vm, actual); + /* We want the balloon size stored in domain definition to + * account for the actual size of virtio-mem too. But the + * balloon size as reported by QEMU (@actual) contains just + * the balloon size without any virtio-mem. Do a wee bit of + * math to fix it. */ + VIR_DEBUG("balloon size before fix is %lld", actual); + for (i = 0; i < vm->def->nmems; i++) { + if (vm->def->mems[i]->model == VIR_DOMAIN_MEMORY_MODEL_VIRTIO_MEM) + actual += vm->def->mems[i]->actualsize; + } + VIR_DEBUG("Updating balloon from %lld to %lld kb", vm->def->mem.cur_balloon, actual); vm->def->mem.cur_balloon = actual; @@ -2429,6 +2441,7 @@ qemuProcessRefreshBalloonState(virQEMUDriver *driver, int asyncJob) { unsigned long long balloon; + size_t i; int rc; /* if no ballooning is available, the current size equals to the current @@ -2445,6 +2458,18 @@ qemuProcessRefreshBalloonState(virQEMUDriver *driver, if (qemuDomainObjExitMonitor(driver, vm) < 0 || rc < 0) return -1; + /* We want the balloon size stored in domain definition to + * account for the actual size of virtio-mem too. But the + * balloon size as reported by QEMU (@balloon) contains just + * the balloon size without any virtio-mem. Do a wee bit of + * math to fix it. */ + VIR_DEBUG("balloon size before fix is %lld", balloon); + for (i = 0; i < vm->def->nmems; i++) { + if (vm->def->mems[i]->model == VIR_DOMAIN_MEMORY_MODEL_VIRTIO_MEM) + balloon += vm->def->mems[i]->actualsize; + } + VIR_DEBUG("Updating balloon from %lld to %lld kb", + vm->def->mem.cur_balloon, balloon); vm->def->mem.cur_balloon = balloon; return 0; -- 2.31.1

New 'update-memory-device' command is introduced which aims on making it user friendly to change <memory/> device. So far I just need to change <requested/> so I'm introducing --requested-size only; but the idea is that this is extensible for other cases too. For instance, want to change <myElement/>? A new --my-element argument can be easily introduced. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; --- docs/manpages/virsh.rst | 30 ++++++++ tools/virsh-domain.c | 149 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 179 insertions(+) diff --git a/docs/manpages/virsh.rst b/docs/manpages/virsh.rst index 87668f2b9a..80802b28ee 100644 --- a/docs/manpages/virsh.rst +++ b/docs/manpages/virsh.rst @@ -4923,6 +4923,36 @@ results as some fields may be autogenerated and thus match devices other than expected. +update-memory-device +-------------------- + +**Syntax:** + +:: + + update-memory-device domain [--print-xml] [--alias alias] + [[--live] [--config] | [--current]] + [--requested-size size] + +This command finds ``<memory/>`` device inside given *domain*, changes +requested values and passes updated device XML to daemon. If *--print-xml* is +specified then the device is not changed, but the updated device XML is printed +to stdout. If there are more than one ``<memory/>`` devices in *domain* use +*--alias* to select the desired one. + +If *--live* is specified, affect a running domain. +If *--config* is specified, affect the next startup of a persistent guest. +If *--current* is specified, it is equivalent to either *--live* or +*--config*, depending on the current state of the guest. +Both *--live* and *--config* flags may be given, but *--current* is +exclusive. Not specifying any flag is the same as specifying *--current*. + +If *--requested-size* is specified then ``<requested/>`` under memory target is +changed to requested *size* (as scaled integer, see ``NOTES`` above). It +defaults to kibibytes if no suffix is provided. The option is valid only for +``virtio-mem`` memory device model. + + change-media ------------ diff --git a/tools/virsh-domain.c b/tools/virsh-domain.c index b69eb3e346..70efca811d 100644 --- a/tools/virsh-domain.c +++ b/tools/virsh-domain.c @@ -9107,6 +9107,149 @@ cmdSetmaxmem(vshControl *ctl, const vshCmd *cmd) return ret; } + +/* + * "update-memory-device" command + */ +static const vshCmdInfo info_update_memory_device[] = { + {.name = "help", + .data = N_("update memory device of a domain") + }, + {.name = "desc", + .data = N_("Update values of a memory device of a domain") + }, + {.name = NULL} +}; + +static const vshCmdOptDef opts_update_memory_device[] = { + VIRSH_COMMON_OPT_DOMAIN_FULL(0), + VIRSH_COMMON_OPT_DOMAIN_CONFIG, + VIRSH_COMMON_OPT_DOMAIN_LIVE, + VIRSH_COMMON_OPT_DOMAIN_CURRENT, + {.name = "print-xml", + .type = VSH_OT_BOOL, + .help = N_("print updated memory device XML instead of executing the change") + }, + {.name = "alias", + .type = VSH_OT_STRING, + .completer = virshDomainDeviceAliasCompleter, + .help = N_("memory device alias"), + }, + {.name = "requested-size", + .type = VSH_OT_INT, + .help = N_("new value of <requested/> size, as scaled integer (default KiB)") + }, + {.name = NULL} +}; + +static int +virshGetUpdatedMemoryXML(char **updatedMemoryXML, + vshControl *ctl, + const vshCmd *cmd, + virDomainPtr dom, + unsigned int flags) +{ + const char *alias = NULL; + g_autoptr(xmlDoc) doc = NULL; + g_autoptr(xmlXPathContext) ctxt = NULL; + g_autofree char *xpath = NULL; + int nmems; + g_autofree xmlNodePtr *mems = NULL; + unsigned int domainXMLFlags = 0; + + if (flags & VIR_DOMAIN_AFFECT_CONFIG) + domainXMLFlags |= VIR_DOMAIN_XML_INACTIVE; + + if (virshDomainGetXMLFromDom(ctl, dom, domainXMLFlags, &doc, &ctxt) < 0) + return -1; + + if (vshCommandOptStringReq(ctl, cmd, "alias", &alias) < 0) + return -1; + + if (alias) { + xpath = g_strdup_printf("/domain/devices/memory[./alias/@name='%s']", alias); + } else { + xpath = g_strdup("/domain/devices/memory"); + } + + nmems = virXPathNodeSet(xpath, ctxt, &mems); + if (nmems < 0) { + vshSaveLibvirtError(); + return -1; + } else if (nmems == 0) { + vshError(ctl, _("no memory device found")); + return -1; + } else if (nmems > 1) { + vshError(ctl, _("multiple memory devices found, use --alias to select one")); + return -1; + } + + ctxt->node = mems[0]; + + if (vshCommandOptBool(cmd, "requested-size")) { + xmlNodePtr requestedSizeNode; + g_autofree char *kibibytesStr = NULL; + unsigned long long bytes = 0; + unsigned long kibibytes = 0; + + if (vshCommandOptScaledInt(ctl, cmd, "requested-size", &bytes, 1024, ULLONG_MAX) < 0) + return -1; + kibibytes = VIR_DIV_UP(bytes, 1024); + + requestedSizeNode = virXPathNode("./target/requested", ctxt); + + if (!requestedSizeNode) { + vshError(ctl, _("virtio-mem device is missing <requested/>")); + return -1; + } + + kibibytesStr = g_strdup_printf("%lu", kibibytes); + xmlNodeSetContent(requestedSizeNode, BAD_CAST kibibytesStr); + } + + if (!(*updatedMemoryXML = virXMLNodeToString(doc, mems[0]))) { + vshSaveLibvirtError(); + return -1; + } + + return 0; +} + +static bool +cmdUpdateMemoryDevice(vshControl *ctl, const vshCmd *cmd) +{ + g_autoptr(virshDomain) dom = NULL; + bool config = vshCommandOptBool(cmd, "config"); + bool live = vshCommandOptBool(cmd, "live"); + bool current = vshCommandOptBool(cmd, "current"); + g_autofree char *updatedMemoryXML = NULL; + unsigned int flags = VIR_DOMAIN_AFFECT_CURRENT; + + VSH_EXCLUSIVE_OPTIONS_VAR(current, live); + VSH_EXCLUSIVE_OPTIONS_VAR(current, config); + + if (config) + flags |= VIR_DOMAIN_AFFECT_CONFIG; + if (live) + flags |= VIR_DOMAIN_AFFECT_LIVE; + + if (!(dom = virshCommandOptDomain(ctl, cmd, NULL))) + return false; + + if (virshGetUpdatedMemoryXML(&updatedMemoryXML, ctl, cmd, dom, flags) < 0) + return false; + + if (vshCommandOptBool(cmd, "print-xml")) { + vshPrint(ctl, "%s", updatedMemoryXML); + } else { + if (virDomainUpdateDeviceFlags(dom, updatedMemoryXML, flags) < 0) + return false; + } + + return true; +} + + /* * "memtune" command */ @@ -15024,6 +15167,12 @@ const vshCmdDef domManagementCmds[] = { .info = info_update_device, .flags = 0 }, + {.name = "update-memory-device", + .handler = cmdUpdateMemoryDevice, + .opts = opts_update_memory_device, + .info = info_update_memory_device, + .flags = 0 + }, {.name = "vcpucount", .handler = cmdVcpucount, .opts = opts_vcpucount, -- 2.31.1

This commit adds new memorydevices.rst page which should serve all models of memory devices. Yet, I'm documenting virtio-mem quirks only. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; --- docs/kbase/index.rst | 4 + docs/kbase/memorydevices.rst | 150 +++++++++++++++++++++++++++++++++++ docs/kbase/meson.build | 1 + 3 files changed, 155 insertions(+) create mode 100644 docs/kbase/memorydevices.rst diff --git a/docs/kbase/index.rst b/docs/kbase/index.rst index 91083ee49d..6355fe4f1d 100644 --- a/docs/kbase/index.rst +++ b/docs/kbase/index.rst @@ -52,6 +52,10 @@ Usage `PCI topology <../pci-addresses.html>`__ Addressing schemes for PCI devices +`Memory devices <memorydevices.html>`__ + Memory devices and their use + + Internals / Debugging --------------------- diff --git a/docs/kbase/memorydevices.rst b/docs/kbase/memorydevices.rst new file mode 100644 index 0000000000..23ccd6da88 --- /dev/null +++ b/docs/kbase/memorydevices.rst @@ -0,0 +1,150 @@ +============== +Memory devices +============== + +.. contents:: + +Basics +====== + +Memory devices can be divided into two families: volatile and non-volatile. +The former is typical RAM memory: it's volatile and thus its contents doesn't +survive reboots nor guest shut downs and power ons. The latter retains its +contents across reboots or power outages. + +In Libvirt, there are two models for volatile memory: + +* ``dimm`` model: + + :: + + <memory model='dimm'> + <target> + <size unit='KiB'>523264</size> + <node>0</node> + </target> + <address type='dimm' slot='0'/> + </memory> + +* ``virtio-mem`` model: + + :: + + <memory model='virtio-mem'> + <target> + <size unit='KiB'>1048576</size> + <node>0</node> + <block unit='KiB'>2048</block> + <requested unit='KiB'>524288</requested> + </target> + <address type='pci' domain='0x0000' bus='0x00' slot='0x02' function='0x0'/> + </memory> + +Then there are two models for non-volatile memory: + +* ``nvidmm`` model: + + :: + + <memory model='nvdimm'> + <source> + <path>/tmp/nvdimm</path> + </source> + <target> + <size unit='KiB'>523264</size> + <node>0</node> + </target> + <address type='dimm' slot='0'/> + </memory> + +* ``virtio-pmem`` model: + + :: + + <memory model='virtio-pmem' access='shared'> + <source> + <path>/tmp/virtio_pmem</path> + </source> + <target> + <size unit='KiB'>524288</size> + </target> + <address type='pci' domain='0x0000' bus='0x00' slot='0x05' function='0x0'/> + </memory> + + +Please note that (maybe somewhat surprisingly) virtio models go onto PCI bus +instead of DIMM slots. + +Furthermore, DIMMs can have ``<source/>`` element which configures backend for +devices. For NVDIMMs the element is mandatory and reflects where the contents +is saved. + +See `memory devices documentation <../formatdomain.html#elementsMemory>`_. + +``virtio-mem`` model +==================== + +The ``virtio-mem`` model can be viewed as revised memory balloon. It offers +adding and removing memory (without the actual hotplug of the device). It +solves problems that memory balloon can't solve on its own and thus is more +flexible than DIMM + balloon solution. ``virtio-mem`` is NUMA aware, and thus +memory can be inflated/deflated only for a subset of guest NUMA nodes. Also, +it works with chunks that are either exposed to guest or taken back from it. + +See https://virtio-mem.gitlab.io/ + +Under the hood, ``virtio-mem`` device is split into chunks of equal size which +are then exposed to the guest. Either all of them or only a portion depending +on user's request. Therefore there are three important sizes for +``virtio-mem``. All are to be found under ``<target/>`` element: + +#. The maximum size the device can ever offer, exposed under ``<size/>`` +#. The size of a single block, exposed under ``<block/>`` +#. The current size exposed to the guest, exposed under ``<requested/>`` + +For instance, the following example the maximum size is 4GiB, the block size is +2MiB and only 1GiB should be exposed to the guest: + + :: + + <memory model='virtio-mem'> + <target> + <size unit='KiB'>4194304</size> + <block unit='KiB'>2048</block> + <requested unit='KiB'>1048576</requested> + </target> + </memory> + +Please note that ``<requested/>`` must be an integer multiple of ``<block/>`` +size or zero (no blocks exposed to the guest) and has to be less or equal to +``<size/>`` (all blocks exposed to the guest). Furthermore, QEMU recommends the +``<block/>`` size to be as big as a Transparent Huge Page (usually 2MiB). + +To change the size exposed to the guest, users should pass memory device XML +with nothing but ``<requested/>`` changed into the +``virDomainUpdateDeviceFlags()`` API. For user's convenience this can be done +via virsh too: + + :: + + # virsh update-memory-device $dom --requested-size 2GiB + +If there are two or more ``<memory/>`` devices then ``--alias`` shall be used +to tell virsh which memory device should be updated. + +For running guests there is fourth size that can be found under ``<target/>``: + + :: + + <actual unit='KiB'>2097152</actual> + +The ``<actual/>`` reflects the actual size used by the guest. In general it +can differ from ``<requested/>``. Reasons include guest kernel missing +``virtio-mem`` module and thus being unable to take offered memory, or guest +kernel being unable to free memory. Since ``<actual/>`` only reports size to +users, the element is never parsed. It is formatted only into live XML. + +Since changing actual allocation requires cooperation with guest kernel, +requests for change are not instant. Therefore, libvirt emits +``VIR_DOMAIN_EVENT_ID_MEMORY_DEVICE_SIZE_CHANGE`` event whenever actual +allocation changed. diff --git a/docs/kbase/meson.build b/docs/kbase/meson.build index 7631b47018..f93f687efb 100644 --- a/docs/kbase/meson.build +++ b/docs/kbase/meson.build @@ -10,6 +10,7 @@ docs_kbase_files = [ 'locking-lockd', 'locking', 'locking-sanlock', + 'memorydevices', 'merging_disk_image_chains', 'migrationinternals', 'qemu-passthrough-security', -- 2.31.1