qemu-arm
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH v2 3/3] qom: Link multiple numa nodes to device using a new o


From: Alex Williamson
Subject: Re: [PATCH v2 3/3] qom: Link multiple numa nodes to device using a new object
Date: Mon, 9 Oct 2023 15:16:11 -0600

On Sun, 8 Oct 2023 01:47:40 +0530
<ankita@nvidia.com> wrote:

> From: Ankit Agrawal <ankita@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 <ankita@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'
>    } }
>  
>  ##




reply via email to

[Prev in Thread] Current Thread [Next in Thread]