On Thu, Oct 29, 2020 at 03:55:36PM +0000, Dario Faggioli wrote:
> This patch introduces the:
>
> <maxphysaddr mode='passthrough'/>
> <maxphysaddr mode='emulate' bits='42'/>
>
> sub element of /domain/cpu.
That makes sense as a location.
>
> Purpose is being able to have a guest see the physical address size
> exactly as the host does (if mode='passthrough' is used) or any size
> the user wants it to see (if mode='emulate' is used and bits='' is
> specified).
>
> This can be useful if the VM needs to have a large amount of memory.
I notice that QEMU recently (well in 2018) introduced a further
option "host-phys-bits-limit". This says to use host phys bits,
but cap it at a certain level. I don't see that this does anything
that we can't already do with the existing "phys-bits" setting
though - it merely automates the lookup of the host bits. So I
don't think we particlarly need host-phys-bits-limit in libvirt.
What I think we do want though is for the <capabilities> XML to
report the host CPU's phys bits, so mgmt apps can query this
and use it to decide on a suitable guest limit.
We have ABIs for checking guest ABI compatibility, which should
probably validate these new settings somewhree.
>
> Signed-off-by: Dario Faggioli <dfaggioli@xxxxxxxx>
> ---
> docs/formatdomain.rst | 21 ++++++++
> docs/schemas/cputypes.rng | 19 +++++++
> src/conf/cpu_conf.c | 52 ++++++++++++++++++++
> src/conf/cpu_conf.h | 17 +++++++
> src/libvirt_private.syms | 2 +
> .../genericxml2xmlindata/cpu-phys-bits-emulate.xml | 20 ++++++++
> .../cpu-phys-bits-passthrough.xml | 20 ++++++++
> tests/genericxml2xmltest.c | 3 +
> 8 files changed, 154 insertions(+)
> create mode 100644 tests/genericxml2xmlindata/cpu-phys-bits-emulate.xml
> create mode 100644 tests/genericxml2xmlindata/cpu-phys-bits-passthrough.xml
>
> diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst
> index ae635bedff..851391011f 100644
> --- a/docs/formatdomain.rst
> +++ b/docs/formatdomain.rst
> @@ -1207,6 +1207,7 @@ following collection of elements. :since:`Since 0.7.5`
> <vendor>Intel</vendor>
> <topology sockets='1' dies='1' cores='2' threads='1'/>
> <cache level='3' mode='emulate'/>
> + <maxphysaddr mode='emulate' bits='42'>
> <feature policy='disable' name='lahf_lm'/>
> </cpu>
> ...
> @@ -1223,6 +1224,7 @@ following collection of elements. :since:`Since 0.7.5`
>
> <cpu mode='host-passthrough' migratable='off'>
> <cache mode='passthrough'/>
> + <maxphysaddr mode='passthrough'>
> <feature policy='disable' name='lahf_lm'/>
> ...
>
> @@ -1446,6 +1448,25 @@ In case no restrictions need to be put on CPU model and its features, a simpler
> The virtual CPU will report no CPU cache of the specified level (or no
> cache at all if the ``level`` attribute is missing).
>
> +``maxphysaddress``
> + :since:`Since 6.10.0` the ``maxphysaddr`` element specifies the size in bits
> + of the physical addresses. The default behavior is that the vCPUs will see
> + what it is configured by default in the hypervisor itself.
> +
> + ``mode``
> + The following values are supported:
> +
> + ``passthrough``
> + The number of physical address bits reported by the host CPU will be
> + passed through to the virtual CPUs
> + ``emulate``
> + The hypervisor will define a specific value for the number of bits
> + of physical addresses via the ``bits`` arrtibute, which is mandatory.
> +
> + ``bits``
> + The number of bits of the physical addresses that the vCPUs should see,
> + if the ``mode`` attribute is set to ``emulate``.
> +
> Guest NUMA topology can be specified using the ``numa`` element. :since:`Since
> 0.9.8`
>
> diff --git a/docs/schemas/cputypes.rng b/docs/schemas/cputypes.rng
> index aea6ff0267..232115226a 100644
> --- a/docs/schemas/cputypes.rng
> +++ b/docs/schemas/cputypes.rng
> @@ -299,6 +299,22 @@
> </element>
> </define>
>
> + <define name="cpuMaxPhysAddr">
> + <element name="maxphysaddr">
> + <attribute name="mode">
> + <choice>
> + <value>emulate</value>
> + <value>passthrough</value>
> + </choice>
> + </attribute>
> + <optional>
> + <attribute name="bits">
> + <ref name="unsignedInt"/>
> + </attribute>
> + </optional>
> + </element>
> + </define>
> +
> <define name="hostcpu">
> <element name="cpu">
> <element name="arch">
> @@ -410,6 +426,9 @@
> <optional>
> <ref name="cpuCache"/>
> </optional>
> + <optional>
> + <ref name="cpuMaxPhysAddr"/>
> + </optional>
> </interleave>
> </element>
> </define>
> diff --git a/src/conf/cpu_conf.c b/src/conf/cpu_conf.c
> index 7778e01131..a151bbf45b 100644
> --- a/src/conf/cpu_conf.c
> +++ b/src/conf/cpu_conf.c
> @@ -83,6 +83,11 @@ VIR_ENUM_IMPL(virCPUCacheMode,
> "disable",
> );
>
> +VIR_ENUM_IMPL(virCPUMaxPhysAddrMode,
> + VIR_CPU_MAX_PHYS_ADDR_MODE_LAST,
> + "emulate",
> + "passthrough",
> +);
>
> virCPUDefPtr virCPUDefNew(void)
> {
> @@ -128,6 +133,7 @@ virCPUDefFree(virCPUDefPtr def)
> if (g_atomic_int_dec_and_test(&def->refs)) {
> virCPUDefFreeModel(def);
> VIR_FREE(def->cache);
> + VIR_FREE(def->addr);
> VIR_FREE(def->tsc);
> VIR_FREE(def);
> }
> @@ -250,6 +256,11 @@ virCPUDefCopyWithoutModel(const virCPUDef *cpu)
> *copy->cache = *cpu->cache;
> }
>
> + if (cpu->addr) {
> + copy->addr = g_new0(virCPUMaxPhysAddrDef, 1);
> + *copy->addr = *cpu->addr;
> + }
> +
> if (cpu->tsc) {
> copy->tsc = g_new0(virHostCPUTscInfo, 1);
> *copy->tsc = *cpu->tsc;
> @@ -670,6 +681,38 @@ virCPUDefParseXML(xmlXPathContextPtr ctxt,
> def->cache->mode = mode;
> }
>
> + if (virXPathInt("count(./maxphysaddr)", ctxt, &n) < 0) {
> + return -1;
> + } else if (n > 1) {
> + virReportError(VIR_ERR_XML_ERROR, "%s",
> + _("at most one CPU maximum physical address bits "
> + "element may be specified"));
> + return -1;
> + } else if (n == 1) {
> + int bits = -1;
> + g_autofree char *strmode = NULL;
> + int mode;
> +
> + if (virXPathBoolean("boolean(./maxphysaddr[1]/@bits)", ctxt) == 1 &&
> + (virXPathInt("string(./maxphysaddr[1]/@bits)", ctxt, &bits) < 0 ||
> + bits < 0)) {
> + virReportError(VIR_ERR_XML_ERROR, "%s",
> + _("CPU maximum physical address bits < 0"));
> + return -1;
> + }
> +
> + if (!(strmode = virXPathString("string(./maxphysaddr[1]/@mode)", ctxt)) ||
> + (mode = virCPUMaxPhysAddrModeTypeFromString(strmode)) < 0) {
> + virReportError(VIR_ERR_XML_ERROR, "%s",
> + _("missing or invalid CPU maximum physical "
> + "address bits mode"));
> + return -1;
> + }
> +
> + def->addr = g_new0(virCPUMaxPhysAddrDef, 1);
> + def->addr->bits = bits;
> + def->addr->mode = mode;
> + }
> *cpu = g_steal_pointer(&def);
> return 0;
> }
> @@ -841,6 +884,15 @@ virCPUDefFormatBuf(virBufferPtr buf,
> virBufferAddLit(buf, "/>\n");
> }
>
> + if (def->addr) {
> + virBufferAddLit(buf, "<maxphysaddr ");
> + if (def->addr->bits != -1)
> + virBufferAsprintf(buf, "bits='%d' ", def->addr->bits);
> + virBufferAsprintf(buf, "mode='%s'",
> + virCPUMaxPhysAddrModeTypeToString(def->addr->mode));
> + virBufferAddLit(buf, "/>\n");
> + }
> +
> for (i = 0; i < def->nfeatures; i++) {
> virCPUFeatureDefPtr feature = def->features + i;
>
> diff --git a/src/conf/cpu_conf.h b/src/conf/cpu_conf.h
> index 3ef14b7932..e7bbe916a3 100644
> --- a/src/conf/cpu_conf.h
> +++ b/src/conf/cpu_conf.h
> @@ -117,6 +117,22 @@ struct _virCPUCacheDef {
> virCPUCacheMode mode;
> };
>
> +typedef enum {
> + VIR_CPU_MAX_PHYS_ADDR_MODE_EMULATE,
> + VIR_CPU_MAX_PHYS_ADDR_MODE_PASSTHROUGH,
> +
> + VIR_CPU_MAX_PHYS_ADDR_MODE_LAST
> +} virCPUMaxPhysAddrMode;
> +
> +VIR_ENUM_DECL(virCPUMaxPhysAddrMode);
> +
> +typedef struct _virCPUMaxPhysAddrDef virCPUMaxPhysAddrDef;
> +typedef virCPUMaxPhysAddrDef *virCPUMaxPhysAddrDefPtr;
> +struct _virCPUMaxPhysAddrDef {
> + int bits; /* -1 for unspecified */
> + virCPUMaxPhysAddrMode mode;
> +};
> +
>
> typedef struct _virCPUDef virCPUDef;
> typedef virCPUDef *virCPUDefPtr;
> @@ -140,6 +156,7 @@ struct _virCPUDef {
> size_t nfeatures_max;
> virCPUFeatureDefPtr features;
> virCPUCacheDefPtr cache;
> + virCPUMaxPhysAddrDefPtr addr;
> virHostCPUTscInfoPtr tsc;
> virTristateSwitch migratable; /* for host-passthrough mode */
> };
> diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms
> index 95e50835ad..8629f81d33 100644
> --- a/src/libvirt_private.syms
> +++ b/src/libvirt_private.syms
> @@ -117,6 +117,8 @@ virCPUDefParseXMLString;
> virCPUDefRef;
> virCPUDefStealModel;
> virCPUDefUpdateFeature;
> +virCPUMaxPhysAddrModeTypeFromString;
> +virCPUMaxPhysAddrModeTypeToString;
> virCPUModeTypeToString;
>
>
> diff --git a/tests/genericxml2xmlindata/cpu-phys-bits-emulate.xml b/tests/genericxml2xmlindata/cpu-phys-bits-emulate.xml
> new file mode 100644
> index 0000000000..0b1b0f1672
> --- /dev/null
> +++ b/tests/genericxml2xmlindata/cpu-phys-bits-emulate.xml
> @@ -0,0 +1,20 @@
> +<domain type='kvm'>
> + <name>foo</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>
> + <cpu mode='host-passthrough'>
> + <maxphysaddr bits='42' mode='emulate'/>
> + </cpu>
> + <clock offset='utc'/>
> + <on_poweroff>destroy</on_poweroff>
> + <on_reboot>restart</on_reboot>
> + <on_crash>destroy</on_crash>
> + <devices>
> + </devices>
> +</domain>
> diff --git a/tests/genericxml2xmlindata/cpu-phys-bits-passthrough.xml b/tests/genericxml2xmlindata/cpu-phys-bits-passthrough.xml
> new file mode 100644
> index 0000000000..cce676eaa6
> --- /dev/null
> +++ b/tests/genericxml2xmlindata/cpu-phys-bits-passthrough.xml
> @@ -0,0 +1,20 @@
> +<domain type='kvm'>
> + <name>foo</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>
> + <cpu mode='host-passthrough'>
> + <maxphysaddr mode='passthrough'/>
> + </cpu>
> + <clock offset='utc'/>
> + <on_poweroff>destroy</on_poweroff>
> + <on_reboot>restart</on_reboot>
> + <on_crash>destroy</on_crash>
> + <devices>
> + </devices>
> +</domain>
> diff --git a/tests/genericxml2xmltest.c b/tests/genericxml2xmltest.c
> index 5110bfba86..6c1c6e699f 100644
> --- a/tests/genericxml2xmltest.c
> +++ b/tests/genericxml2xmltest.c
> @@ -256,6 +256,9 @@ mymain(void)
>
> DO_TEST_BACKUP_FULL("backup-pull-internal-invalid", true);
>
> + DO_TEST("cpu-phys-bits-emulate");
> + DO_TEST("cpu-phys-bits-passthrough");
> +
>
> virObjectUnref(caps);
> virObjectUnref(xmlopt);
>
>
Regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
