On Sun, 8 Oct 2023 01:47:40 +0530 <ank...@nvidia.com> wrote: > From: Ankit Agrawal <ank...@nvidia.com> > > NVIDIA GPU's support MIG (Mult-Instance GPUs) feature [1], which allows > partitioning of the GPU device resources (including device memory) into > several (upto 8) isolated instances. Each of the partitioned memory needs > a dedicated NUMA node to operate. The partitions are not fixed and they > can be created/deleted at runtime. > > Unfortunately Linux OS does not provide a means to dynamically create/destroy > NUMA nodes and such feature implementation is not expected to be trivial. The > nodes that OS discovers at the boot time while parsing SRAT remains fixed. So > we utilize the GI Affinity structures that allows association between nodes > and devices. Multiple GI structures per BDF is possible, allowing creation of > multiple nodes by exposing unique PXM in each of these structures. > > Introducing a new nvidia-acpi-generic-initiator object, which inherits from > the generic acpi-generic-initiator object to allow a BDF to be associated with > more than 1 nodes. > > An admin can provide the range of nodes using numa-node-start and > numa-node-count and link it to a device by providing its id. The following > sample creates 8 nodes and link them to the device dev0: > > -numa node,nodeid=2 \ > -numa node,nodeid=3 \ > -numa node,nodeid=4 \ > -numa node,nodeid=5 \ > -numa node,nodeid=6 \ > -numa node,nodeid=7 \ > -numa node,nodeid=8 \ > -numa node,nodeid=9 \ > -device > vfio-pci-nohotplug,host=0009:01:00.0,bus=pcie.0,addr=04.0,rombar=0,id=dev0 \ > -object > nvidia-acpi-generic-initiator,id=gi0,device=dev0,numa-node-start=2,numa-node-count=8 > \
Why didn't we just implement start and count in the base object (or a list)? It seems like this gives the nvidia-acpi-generic-initiator two different ways to set gi->node, either node= of the parent or numa-node-start= here. Once we expose the implicit node count in the base object, I'm not sure the purpose of this object. I would have thought it for keying the build of the NVIDIA specific _DSD, but that's not implemented in this version. I also don't see any programatic means for management tools to know how many nodes to create. For example what happens if there's a MIGv2 that supports 16 partitions by default and makes use of the same vfio-pci variant driver? Thanks, Alex > > [1] https://www.nvidia.com/en-in/technologies/multi-instance-gpu > > Signed-off-by: Ankit Agrawal <ank...@nvidia.com> > --- > hw/acpi/acpi-generic-initiator.c | 61 ++++++++++++++++++++++++ > include/hw/acpi/acpi-generic-initiator.h | 12 +++++ > qapi/qom.json | 24 +++++++++- > 3 files changed, 95 insertions(+), 2 deletions(-) > > diff --git a/hw/acpi/acpi-generic-initiator.c > b/hw/acpi/acpi-generic-initiator.c > index 1ae79639be..8ef887c3a4 100644 > --- a/hw/acpi/acpi-generic-initiator.c > +++ b/hw/acpi/acpi-generic-initiator.c > @@ -150,3 +150,64 @@ void build_srat_generic_initiator(GArray *table_data) > } > g_slist_free(list); > } > + > +static void > +nvidia_acpi_generic_initiator_set_node_start(Object *obj, Visitor *v, > + const char *name, void *opaque, > + Error **errp) > +{ > + AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); > + uint32_t value; > + > + if (!visit_type_uint32(v, name, &value, errp)) { > + return; > + } > + > + if (value >= MAX_NODES) { > + return; > + } > + > + gi->node = value; > +} > + > +static void > +nvidia_acpi_generic_initiator_set_node_count(Object *obj, Visitor *v, > + const char *name, void *opaque, > + Error **errp) > +{ > + AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); > + uint32_t value; > + > + if (!visit_type_uint32(v, name, &value, errp)) { > + return; > + } > + > + gi->node_count = value; > +} > + > +static void nvidia_acpi_generic_initiator_class_init(ObjectClass *oc, void > *data) > +{ > + object_class_property_add(oc, > NVIDIA_ACPI_GENERIC_INITIATOR_NODE_START_PROP, > + "uint32", NULL, > + nvidia_acpi_generic_initiator_set_node_start, > + NULL, NULL); > + object_class_property_add(oc, > NVIDIA_ACPI_GENERIC_INITIATOR_NODE_COUNT_PROP, > + "uint32", NULL, > + nvidia_acpi_generic_initiator_set_node_count, > + NULL, NULL); > +} > + > +static const TypeInfo nvidia_acpi_generic_initiator_info = { > + .parent = TYPE_ACPI_GENERIC_INITIATOR, > + .name = TYPE_NVIDIA_ACPI_GENERIC_INITIATOR, > + .instance_size = sizeof(NvidiaAcpiGenericInitiator), > + .class_size = sizeof(NvidiaAcpiGenericInitiatorClass), > + .class_init = nvidia_acpi_generic_initiator_class_init, > +}; > + > +static void > +nvidia_acpi_generic_initiator_register_types(void) > +{ > + type_register_static(&nvidia_acpi_generic_initiator_info); > +} > +type_init(nvidia_acpi_generic_initiator_register_types); > diff --git a/include/hw/acpi/acpi-generic-initiator.h > b/include/hw/acpi/acpi-generic-initiator.h > index e8e2670309..3e4cf42064 100644 > --- a/include/hw/acpi/acpi-generic-initiator.h > +++ b/include/hw/acpi/acpi-generic-initiator.h > @@ -9,10 +9,14 @@ > #include "qom/object_interfaces.h" > > #define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator" > +#define TYPE_NVIDIA_ACPI_GENERIC_INITIATOR "nvidia-acpi-generic-initiator" > > #define ACPI_GENERIC_INITIATOR_DEVICE_PROP "device" > #define ACPI_GENERIC_INITIATOR_NODE_PROP "node" > > +#define NVIDIA_ACPI_GENERIC_INITIATOR_NODE_START_PROP "numa-node-start" > +#define NVIDIA_ACPI_GENERIC_INITIATOR_NODE_COUNT_PROP "numa-node-count" > + > typedef struct AcpiGenericInitiator { > /* private */ > Object parent; > @@ -47,6 +51,14 @@ typedef struct PCIDeviceHandle { > uint64_t res1; > } PCIDeviceHandle; > > +typedef struct NvidiaAcpiGenericInitiator { > + AcpiGenericInitiator parent; > +} NvidiaAcpiGenericInitiator; > + > +typedef struct NvidiaAcpiGenericInitiatorClass { > + AcpiGenericInitiatorClass parent_class; > +} NvidiaAcpiGenericInitiatorClass; > + > void build_srat_generic_initiator(GArray *table_data); > > #endif > diff --git a/qapi/qom.json b/qapi/qom.json > index 86c87a161c..c29ad1388d 100644 > --- a/qapi/qom.json > +++ b/qapi/qom.json > @@ -793,6 +793,24 @@ > { 'struct': 'AcpiGenericInitiatorProperties', > 'data': { 'device': 'str', 'node': 'uint32' } } > > +## > +# @NvidiaAcpiGenericInitiatorProperties: > +# > +# Properties for nvidia-acpi-generic-initiator objects. > +# > +# @device: the ID of the device to be associated with the nodes > +# > +# @numa-node-start: the ID of the numa node > +# > +# @numa-node-count: count of the numa nodes assocuated with the device > +# > +# Since: 8.0 > +## > +{ 'struct': 'NvidiaAcpiGenericInitiatorProperties', > + 'data': { 'device': 'str', > + 'numa-node-start': 'uint32', > + 'numa-node-count': 'uint32' } } > + > ## > # @RngProperties: > # > @@ -962,7 +980,8 @@ > 'tls-cipher-suites', > { 'name': 'x-remote-object', 'features': [ 'unstable' ] }, > { 'name': 'x-vfio-user-server', 'features': [ 'unstable' ] }, > - 'acpi-generic-initiator' > + 'acpi-generic-initiator', > + 'nvidia-acpi-generic-initiator' > ] } > > ## > @@ -1030,7 +1049,8 @@ > 'tls-cipher-suites': 'TlsCredsProperties', > 'x-remote-object': 'RemoteObjectProperties', > 'x-vfio-user-server': 'VfioUserServerProperties', > - 'acpi-generic-initiator': 'AcpiGenericInitiatorProperties' > + 'acpi-generic-initiator': 'AcpiGenericInitiatorProperties', > + 'nvidia-acpi-generic-initiator': > 'NvidiaAcpiGenericInitiatorProperties' > } } > > ##
