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 Generic Initiator 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.
Introduce a new acpi-generic-initiator object to allow host admin provide the
device and the corresponding NUMA nodes. Qemu maintain this association and
use this object to build the requisite GI Affinity Structure.
An admin can provide the range of nodes through a uint16 array host-nodes
and link it to a device by providing its id. Currently, only PCI device is
supported. The following sample creates 8 nodes and link them to the PCI
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 acpi-generic-initiator,id=gi0,pci-dev=dev0,host-nodes=2-9 \
[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 | 70 ++++++++++++++++++++++++
hw/acpi/meson.build | 1 +
include/hw/acpi/acpi-generic-initiator.h | 27 +++++++++
qapi/qom.json | 17 ++++++
4 files changed, 115 insertions(+)
create mode 100644 hw/acpi/acpi-generic-initiator.c
create mode 100644 include/hw/acpi/acpi-generic-initiator.h
diff --git a/hw/acpi/acpi-generic-initiator.c b/hw/acpi/acpi-generic-initiator.c
new file mode 100644
index 0000000000..e05e28e962
--- /dev/null
+++ b/hw/acpi/acpi-generic-initiator.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include "qemu/osdep.h"
+#include "hw/acpi/acpi-generic-initiator.h"
+#include "hw/pci/pci_device.h"
+#include "qapi/error.h"
+#include "qapi/qapi-builtin-visit.h"
+#include "qapi/visitor.h"
+#include "qemu/error-report.h"
+
+OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericInitiator, acpi_generic_initiator,
+ ACPI_GENERIC_INITIATOR, OBJECT,
+ { TYPE_USER_CREATABLE },
+ { NULL })
+
+OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericInitiator, ACPI_GENERIC_INITIATOR)
+
+static void acpi_generic_initiator_init(Object *obj)
+{
+ AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+ bitmap_zero(gi->host_nodes, MAX_NODES);
+ gi->pci_dev = NULL;
+}
+
+static void acpi_generic_initiator_finalize(Object *obj)
+{
+ AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+ g_free(gi->pci_dev);
+}
+
+static void acpi_generic_initiator_set_pci_device(Object *obj, const char *val,
+ Error **errp)
+{
+ AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+ gi->pci_dev = g_strdup(val);
+}
+
+static void
+acpi_generic_initiator_set_host_nodes(Object *obj, Visitor *v, const char *name,
+ void *opaque, Error **errp)
+{
+ AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+ uint16List *l = NULL, *host_nodes = NULL;
+
+ visit_type_uint16List(v, name, &host_nodes, errp);
+
+ for (l = host_nodes; l; l = l->next) {
+ if (l->value >= MAX_NODES) {
+ error_setg(errp, "Invalid host-nodes value: %d", l->value);
+ break;
+ } else {
+ bitmap_set(gi->host_nodes, l->value, 1);
+ }
+ }
+
+ qapi_free_uint16List(host_nodes);
+}
+
+static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data)
+{
+ object_class_property_add_str(oc, "pci-dev", NULL,
+ acpi_generic_initiator_set_pci_device);
+ object_class_property_add(oc, "host-nodes", "int", NULL,
+ acpi_generic_initiator_set_host_nodes, NULL, NULL);
+}
diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build
index fc1b952379..2268589519 100644
--- a/hw/acpi/meson.build
+++ b/hw/acpi/meson.build
@@ -1,5 +1,6 @@
acpi_ss = ss.source_set()
acpi_ss.add(files(
+ 'acpi-generic-initiator.c',
'acpi_interface.c',
'aml-build.c',
'bios-linker-loader.c',
diff --git a/include/hw/acpi/acpi-generic-initiator.h b/include/hw/acpi/acpi-generic-initiator.h
new file mode 100644
index 0000000000..41b0c8cda2
--- /dev/null
+++ b/include/hw/acpi/acpi-generic-initiator.h
@@ -0,0 +1,27 @@
+#ifndef ACPI_GENERIC_INITIATOR_H
+#define ACPI_GENERIC_INITIATOR_H
+
+#include "hw/mem/pc-dimm.h"
+#include "hw/acpi/bios-linker-loader.h"
+#include "hw/acpi/aml-build.h"
+#include "sysemu/numa.h"
+#include "qemu/uuid.h"
+#include "qom/object.h"
+#include "qom/object_interfaces.h"
+
+#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator"
+
+typedef struct AcpiGenericInitiator {
+ /* private */
+ Object parent;
+
+ /* public */
+ char *pci_dev;
+ DECLARE_BITMAP(host_nodes, MAX_NODES);
+} AcpiGenericInitiator;
+
+typedef struct AcpiGenericInitiatorClass {
+ ObjectClass parent_class;
+} AcpiGenericInitiatorClass;
+
+#endif
diff --git a/qapi/qom.json b/qapi/qom.json
index c53ef978ff..efcc4b8dfd 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -794,6 +794,21 @@
{ 'struct': 'VfioUserServerProperties',
'data': { 'socket': 'SocketAddress', 'device': 'str' } }
+##
+# @AcpiGenericInitiatorProperties:
+#
+# Properties for acpi-generic-initiator objects.
+#
+# @pci-dev: PCI device ID to be associated with the node
+#
+# @host-nodes: numa node list
+#
+# Since: 9.0
+##
+{ 'struct': 'AcpiGenericInitiatorProperties',
+ 'data': { 'pci-dev': 'str',
+ 'host-nodes': ['uint16'] } }
+
##
# @RngProperties:
#
@@ -911,6 +926,7 @@
##
{ 'enum': 'ObjectType',
'data': [
+ 'acpi-generic-initiator',
'authz-list',
'authz-listfile',
'authz-pam',
@@ -981,6 +997,7 @@
'id': 'str' },
'discriminator': 'qom-type',
'data': {
+ 'acpi-generic-initiator': 'AcpiGenericInitiatorProperties',
'authz-list': 'AuthZListProperties',
'authz-listfile': 'AuthZListFileProperties',
'authz-pam': 'AuthZPAMProperties',
--
2.34.1<ankita@nvidia.com> writes:
> 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 Generic Initiator 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.
>
> Introduce a new acpi-generic-initiator object to allow host admin provide the
> device and the corresponding NUMA nodes. Qemu maintain this association and
> use this object to build the requisite GI Affinity Structure.
Pardon my ignorance... What makes this object an "initiator", and why
is it "generic"?
> An admin can provide the range of nodes through a uint16 array host-nodes
> and link it to a device by providing its id. Currently, only PCI device is
> supported. The following sample creates 8 nodes and link them to the PCI
> 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 acpi-generic-initiator,id=gi0,pci-dev=dev0,host-nodes=2-9 \
Does this link *all* NUMA nodes to dev0?
Would an example involving two devices be more instructive?
> [1] https://www.nvidia.com/en-in/technologies/multi-instance-gpu
>
> Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
[...]
> diff --git a/qapi/qom.json b/qapi/qom.json
> index c53ef978ff..efcc4b8dfd 100644
> --- a/qapi/qom.json
> +++ b/qapi/qom.json
> @@ -794,6 +794,21 @@
> { 'struct': 'VfioUserServerProperties',
> 'data': { 'socket': 'SocketAddress', 'device': 'str' } }
>
> +##
> +# @AcpiGenericInitiatorProperties:
> +#
> +# Properties for acpi-generic-initiator objects.
> +#
> +# @pci-dev: PCI device ID to be associated with the node
> +#
> +# @host-nodes: numa node list
This feels a bit terse. The commit message makes me guess this
specifies the NUMA nodes to be linked to @pci-dev. Correct?
> +#
> +# Since: 9.0
> +##
> +{ 'struct': 'AcpiGenericInitiatorProperties',
> + 'data': { 'pci-dev': 'str',
> + 'host-nodes': ['uint16'] } }
> +
> ##
> # @RngProperties:
> #
> @@ -911,6 +926,7 @@
> ##
> { 'enum': 'ObjectType',
> 'data': [
> + 'acpi-generic-initiator',
> 'authz-list',
> 'authz-listfile',
> 'authz-pam',
> @@ -981,6 +997,7 @@
> 'id': 'str' },
> 'discriminator': 'qom-type',
> 'data': {
> + 'acpi-generic-initiator': 'AcpiGenericInitiatorProperties',
> 'authz-list': 'AuthZListProperties',
> 'authz-listfile': 'AuthZListFileProperties',
> 'authz-pam': 'AuthZPAMProperties',
Thanks Markus for the review.
>> Introduce a new acpi-generic-initiator object to allow host admin provide the
>> device and the corresponding NUMA nodes. Qemu maintain this association and
>> use this object to build the requisite GI Affinity Structure.
>
> Pardon my ignorance... What makes this object an "initiator", and why
> is it "generic"?
In ACPI 6.3 (https://uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf),
a new table in System Resource Affinity Table called Generic initiator Affinity table
was introduced to describe devices such as heterogeneous processors and
accelerators, GPUs, and I/O devices with integrated compute or DMA engines
(termed as Generic Initiator) that are present on the system. It is used to associate
a proximity domain with those devices.
You may refer 5.2.16.6 in the aforementioned link. This patch implements that
structure (Table 5-78) for Qemu ACPI.
>> An admin can provide the range of nodes through a uint16 array host-nodes
>> and link it to a device by providing its id. Currently, only PCI device is
>> supported. The following sample creates 8 nodes and link them to the PCI
>> 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 acpi-generic-initiator,id=gi0,pci-dev=dev0,host-nodes=2-9 \
>
> Does this link *all* NUMA nodes to dev0?
>
> Would an example involving two devices be more instructive?
Sure, updated in v6.
>> diff --git a/qapi/qom.json b/qapi/qom.json
>> index c53ef978ff..efcc4b8dfd 100644
>> --- a/qapi/qom.json
>> +++ b/qapi/qom.json
>> @@ -794,6 +794,21 @@
>> { 'struct': 'VfioUserServerProperties',
>> 'data': { 'socket': 'SocketAddress', 'device': 'str' } }
>>
>> +##
>> +# @AcpiGenericInitiatorProperties:
>> +#
>> +# Properties for acpi-generic-initiator objects.
>> +#
>> +# @pci-dev: PCI device ID to be associated with the node
>> +#
>> +# @host-nodes: numa node list
>
> This feels a bit terse. The commit message makes me guess this
> specifies the NUMA nodes to be linked to @pci-dev. Correct?
Right, it could be made cleared. Done in v6.
© 2016 - 2024 Red Hat, Inc.