* [PATCH v5 1/2] qom: new object to associate device to numa node
2023-12-03 6:02 [PATCH v5 0/2] acpi: report numa nodes for device memory using GI ankita
@ 2023-12-03 6:02 ` ankita
2023-12-22 12:32 ` Markus Armbruster
2023-12-03 6:02 ` [PATCH v5 2/2] hw/acpi: Implement the SRAT GI affinity structure ankita
1 sibling, 1 reply; 5+ messages in thread
From: ankita @ 2023-12-03 6:02 UTC (permalink / raw)
To: ankita, jgg, alex.williamson, clg, shannon.zhaosl, peter.maydell,
ani, berrange, eduardo, imammedo, mst, eblake, armbru, david,
gshan, Jonathan.Cameron
Cc: aniketa, cjia, kwankhede, targupta, vsethi, acurrid, dnigam,
udhoke, qemu-arm, qemu-devel
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
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH v5 2/2] hw/acpi: Implement the SRAT GI affinity structure
2023-12-03 6:02 [PATCH v5 0/2] acpi: report numa nodes for device memory using GI ankita
2023-12-03 6:02 ` [PATCH v5 1/2] qom: new object to associate device to numa node ankita
@ 2023-12-03 6:02 ` ankita
1 sibling, 0 replies; 5+ messages in thread
From: ankita @ 2023-12-03 6:02 UTC (permalink / raw)
To: ankita, jgg, alex.williamson, clg, shannon.zhaosl, peter.maydell,
ani, berrange, eduardo, imammedo, mst, eblake, armbru, david,
gshan, Jonathan.Cameron
Cc: aniketa, cjia, kwankhede, targupta, vsethi, acurrid, dnigam,
udhoke, qemu-arm, qemu-devel
From: Ankit Agrawal <ankita@nvidia.com>
ACPI spec provides a scheme to associate "Generic Initiators" [1]
(e.g. heterogeneous processors and accelerators, GPUs, and I/O devices with
integrated compute or DMA engines GPUs) with Proximity Domains. This is
achieved using Generic Initiator Affinity Structure in SRAT. During bootup,
Linux kernel parse the ACPI SRAT to determine the PXM ids and create a NUMA
node for each unique PXM ID encountered. Qemu currently do not implement
these structures while building SRAT.
Add GI structures while building VM ACPI SRAT. The association between
devices and nodes are stored using acpi-generic-initiator object. Lookup
presence of all such objects and use them to build these structures.
The structure needs a PCI device handle [2] that consists of the device BDF.
The vfio-pci device corresponding to the acpi-generic-initiator object is
located to determine the BDF.
[1] ACPI Spec 6.3, Section 5.2.16.6
[2] ACPI Spec 6.3, Table 5.80
Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
---
hw/acpi/acpi-generic-initiator.c | 99 ++++++++++++++++++++++++
hw/arm/virt-acpi-build.c | 3 +
include/hw/acpi/acpi-generic-initiator.h | 26 +++++++
3 files changed, 128 insertions(+)
diff --git a/hw/acpi/acpi-generic-initiator.c b/hw/acpi/acpi-generic-initiator.c
index e05e28e962..fa5235f2bb 100644
--- a/hw/acpi/acpi-generic-initiator.c
+++ b/hw/acpi/acpi-generic-initiator.c
@@ -68,3 +68,102 @@ static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data)
object_class_property_add(oc, "host-nodes", "int", NULL,
acpi_generic_initiator_set_host_nodes, NULL, NULL);
}
+
+static int acpi_generic_initiator_list(Object *obj, void *opaque)
+{
+ GSList **list = opaque;
+
+ if (object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) {
+ *list = g_slist_append(*list, ACPI_GENERIC_INITIATOR(obj));
+ }
+
+ object_child_foreach(obj, acpi_generic_initiator_list, opaque);
+ return 0;
+}
+
+/*
+ * Identify Generic Initiator objects and link them into the list which is
+ * returned to the caller.
+ *
+ * Note: it is the caller's responsibility to free the list to avoid
+ * memory leak.
+ */
+static GSList *acpi_generic_initiator_get_list(void)
+{
+ GSList *list = NULL;
+
+ object_child_foreach(object_get_root(),
+ acpi_generic_initiator_list, &list);
+ return list;
+}
+
+/*
+ * ACPI 6.3:
+ * Table 5-78 Generic Initiator Affinity Structure
+ */
+static void
+build_srat_generic_pci_initiator_affinity(GArray *table_data, int node,
+ PCIDeviceHandle *handle)
+{
+ uint8_t index;
+
+ build_append_int_noprefix(table_data, 5, 1); /* Type */
+ build_append_int_noprefix(table_data, 32, 1); /* Length */
+ build_append_int_noprefix(table_data, 0, 1); /* Reserved */
+ build_append_int_noprefix(table_data, 1, 1); /* Device Handle Type: PCI */
+ build_append_int_noprefix(table_data, node, 4); /* Proximity Domain */
+
+ /* Device Handle - PCI */
+ build_append_int_noprefix(table_data, handle->segment, 2);
+ build_append_int_noprefix(table_data, handle->bdf, 2);
+ for (index = 0; index < 12; index++) {
+ build_append_int_noprefix(table_data, 0, 1);
+ }
+
+ build_append_int_noprefix(table_data, GEN_AFFINITY_ENABLED, 4); /* Flags */
+ build_append_int_noprefix(table_data, 0, 4); /* Reserved */
+}
+
+void build_srat_generic_pci_initiator(GArray *table_data)
+{
+ GSList *gi_list, *list = acpi_generic_initiator_get_list();
+ AcpiGenericInitiator *gi;
+
+ for (gi_list = list; gi_list; gi_list = gi_list->next) {
+ Object *o;
+ uint16_t node;
+ PCIDevice *pci_dev;
+ bool node_specified = false;
+
+ gi = gi_list->data;
+
+ o = object_resolve_path_type(gi->pci_dev, TYPE_PCI_DEVICE, NULL);
+ if (!o) {
+ error_printf("Specified device must be a PCI device.\n");
+ exit(1);
+ }
+ pci_dev = PCI_DEVICE(o);
+
+ for (node = 0; (node = find_next_bit(gi->host_nodes,
+ MAX_NODES, node)) != MAX_NODES; node++)
+ {
+ PCIDeviceHandle dev_handle;
+ dev_handle.segment = 0;
+ dev_handle.bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)),
+ pci_dev->devfn);
+ build_srat_generic_pci_initiator_affinity(table_data,
+ node, &dev_handle);
+ node_specified = true;
+ }
+
+ if (!node_specified) {
+ error_report("Generic Initiator device 0:%x:%x.%x has no associated"
+ " NUMA node.", pci_bus_num(pci_get_bus(pci_dev)),
+ PCI_SLOT(pci_dev->devfn), PCI_FUNC(pci_dev->devfn));
+ error_printf("Specify NUMA node with -host-nodes option.\n");
+ exit(1);
+ }
+ }
+
+ g_slist_free(list);
+}
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 8bc35a483c..00d77327e0 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -58,6 +58,7 @@
#include "migration/vmstate.h"
#include "hw/acpi/ghes.h"
#include "hw/acpi/viot.h"
+#include "hw/acpi/acpi-generic-initiator.h"
#define ARM_SPI_BASE 32
@@ -558,6 +559,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
}
}
+ build_srat_generic_pci_initiator(table_data);
+
if (ms->nvdimms_state->is_enabled) {
nvdimm_build_srat(table_data);
}
diff --git a/include/hw/acpi/acpi-generic-initiator.h b/include/hw/acpi/acpi-generic-initiator.h
index 41b0c8cda2..4013943319 100644
--- a/include/hw/acpi/acpi-generic-initiator.h
+++ b/include/hw/acpi/acpi-generic-initiator.h
@@ -24,4 +24,30 @@ typedef struct AcpiGenericInitiatorClass {
ObjectClass parent_class;
} AcpiGenericInitiatorClass;
+/*
+ * ACPI 6.3:
+ * Table 5-81 Flags – Generic Initiator Affinity Structure
+ */
+typedef enum {
+ GEN_AFFINITY_ENABLED = (1 << 0), /*
+ * If clear, the OSPM ignores the contents
+ * of the Generic Initiator/Port Affinity
+ * Structure. This allows system firmware
+ * to populate the SRAT with a static
+ * number of structures, but only enable
+ * them as necessary.
+ */
+} GenericAffinityFlags;
+
+/*
+ * ACPI 6.3:
+ * Table 5-80 Device Handle - PCI
+ */
+typedef struct PCIDeviceHandle {
+ uint16_t segment;
+ uint16_t bdf;
+} PCIDeviceHandle;
+
+void build_srat_generic_pci_initiator(GArray *table_data);
+
#endif
--
2.34.1
^ permalink raw reply related [flat|nested] 5+ messages in thread