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 (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.
Implement the mechanism to build the GI affinity structures as Qemu currently
does not. Introduce a new acpi-generic-initiator object to allow host admin
link a device with an associated NUMA node. Qemu maintains this association
and use this object to build the requisite GI Affinity Structure.
When multiple NUMA nodes are associated with a device, it is required to
create those many number of acpi-generic-initiator objects, each representing
a unique device:node association.
Following is one of a decoded GI affinity structure in VM ACPI SRAT.
[0C8h 0200 1] Subtable Type : 05 [Generic Initiator Affinity]
[0C9h 0201 1] Length : 20
[0CAh 0202 1] Reserved1 : 00
[0CBh 0203 1] Device Handle Type : 01
[0CCh 0204 4] Proximity Domain : 00000007
[0D0h 0208 16] Device Handle : 00 00 20 00 00 00 00 00 00 00 00
00 00 00 00 00
[0E0h 0224 4] Flags (decoded below) : 00000001
Enabled : 1
[0E4h 0228 4] Reserved2 : 00000000
[0E8h 0232 1] Subtable Type : 05 [Generic Initiator Affinity]
[0E9h 0233 1] Length : 20
An admin can provide a range of acpi-generic-initiator objects, each
associating a device (by providing the id through pci-dev argument)
to the desired NUMA node (using the node argument). Currently, only PCI
device is supported.
For the grace hopper system, create a range of 8 nodes and associate that
with the device using the acpi-generic-initiator object. While a configuration
of less than 8 nodes per device is allowed, such configuration will prevent
utilization of the feature to the fullest. The following sample creates 8
nodes per PCI device for a VM with 2 PCI devices and link them to the
respecitve PCI device using acpi-generic-initiator objects:
-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,node=2 \
-object acpi-generic-initiator,id=gi1,pci-dev=dev0,node=3 \
-object acpi-generic-initiator,id=gi2,pci-dev=dev0,node=4 \
-object acpi-generic-initiator,id=gi3,pci-dev=dev0,node=5 \
-object acpi-generic-initiator,id=gi4,pci-dev=dev0,node=6 \
-object acpi-generic-initiator,id=gi5,pci-dev=dev0,node=7 \
-object acpi-generic-initiator,id=gi6,pci-dev=dev0,node=8 \
-object acpi-generic-initiator,id=gi7,pci-dev=dev0,node=9 \
-numa node,nodeid=10 -numa node,nodeid=11 -numa node,nodeid=12 \
-numa node,nodeid=13 -numa node,nodeid=14 -numa node,nodeid=15 \
-numa node,nodeid=16 -numa node,nodeid=17 \
-device vfio-pci-nohotplug,host=0009:01:01.0,bus=pcie.0,addr=05.0,rombar=0,id=dev1 \
-object acpi-generic-initiator,id=gi8,pci-dev=dev1,node=10 \
-object acpi-generic-initiator,id=gi9,pci-dev=dev1,node=11 \
-object acpi-generic-initiator,id=gi10,pci-dev=dev1,node=12 \
-object acpi-generic-initiator,id=gi11,pci-dev=dev1,node=13 \
-object acpi-generic-initiator,id=gi12,pci-dev=dev1,node=14 \
-object acpi-generic-initiator,id=gi13,pci-dev=dev1,node=15 \
-object acpi-generic-initiator,id=gi14,pci-dev=dev1,node=16 \
-object acpi-generic-initiator,id=gi15,pci-dev=dev1,node=17 \
Link: https://www.nvidia.com/en-in/technologies/multi-instance-gpu [1]
Cc: Jonathan Cameron <qemu-devel@nongnu.org>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
Message-Id: <20240308145525.10886-2-ankita@nvidia.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
CONFIG_ALL is tricky to use and was ported over to Meson from the
recursive processing of Makefile variables. Meson sourcesets
however have all_sources() and all_dependencies() methods that
remove the need for it.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We use the user_ss[] array to hold the user emulation sources,
and the softmmu_ss[] array to hold the system emulation ones.
Hold the latter in the 'system_ss[]' array for parity with user
emulation.
Mechanical change doing:
$ sed -i -e s/softmmu_ss/system_ss/g $(git grep -l softmmu_ss)
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230613133347.82210-10-philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This moves the command from MAINTAINERS section "QMP" to section
"ACPI/SMBIOS)".
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20230124121946.1139465-25-armbru@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
simplify build_append_pci_bus_devices() a bit by handling bridge
specific logic in bridge dedicated AcpiDevAmlIfClass::build_dev_aml
callback.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-30-imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Although the ICH9 ACPI controller may currently be tied to x86 it
doesn't have to. Furthermore, the source files this configuration switch
manages contain a '9', so this name fits more.
Signed-off-by: Bernhard Beschow <shentey@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20221216130355.41667-2-shentey@gmail.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
tco.c contains the ICH9 implementation of its "total cost
of ownership". Rename it accordingly to emphasis this is
a part of the ICH9 model.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20221212105115.2113-1-philmd@linaro.org>
Acked-by: Igor Mammedov <imammedo@redhat.com>
There is already ISADeviceClass::build_aml() callback which
builds device specific AML blob for some ISA devices.
To extend the same idea to other devices, add TYPE_ACPI_DEV_AML_IF
Interface that will provide a more generic callback which
will be used not only for ISA but other devices. It will
allow get rid of some data-mining and ad-hoc AML building,
by asking device(s) to generate its own AML blob like it's
done for ISA devices.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Message-Id: <20220608135340.3304695-2-imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This implements a PCI device for ACPI ERST. This implements the
non-NVRAM "mode" of operation for ERST as it is supported by
Linux and Windows.
Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
Reviewed-by: Ani Sinha <ani@anisinha.ca>
Message-Id: <1643402289-22216-6-git-send-email-eric.devolder@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add a function that generates a Virtual I/O Translation table (VIOT),
describing the topology of paravirtual IOMMUs. The table is created if a
virtio-iommu device is present. It contains a virtio-iommu node and PCI
Range nodes for endpoints managed by the IOMMU. By default, a single
node describes all PCI devices. When passing the
"default_bus_bypass_iommu" machine option and "bypass_iommu" PXB option,
only buses that do not bypass the IOMMU are described by PCI Range
nodes.
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Message-Id: <20211026182024.2642038-2-jean-philippe@linaro.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Currently various acpi hotplug modules like cpu hotplug, memory hotplug, pci
hotplug, nvdimm hotplug are all pulled in when CONFIG_ACPI_X86 is turned on.
This brings in support for whole lot of subsystems that some targets like
mips does not need. They are added just to satisfy symbol dependencies. This
is ugly and should be avoided. Targets should be able to pull in just what they
need and no more. For example, mips only needs support for PIIX4 and does not
need acpi pci hotplug support or cpu hotplug support or memory hotplug support
etc. This change is an effort to clean this up.
In this change, new config variables are added for various acpi hotplug
subsystems. Targets like mips can only enable PIIX4 support and not the rest
of all the other modules which were being previously pulled in as a part of
CONFIG_ACPI_X86. Function stubs make sure that symbols which piix4 needs but
are not required by mips (for example, symbols specific to pci hotplug etc)
are available to satisfy the dependencies.
Currently, this change only addresses issues with mips malta targets. In future
we might be able to clean up other targets which are similarly pulling in lot
of unnecessary hotplug modules by enabling ACPI_X86.
This change should also address issues such as the following:
https://gitlab.com/qemu-project/qemu/-/issues/221https://gitlab.com/qemu-project/qemu/-/issues/193
Signed-off-by: Ani Sinha <ani@anisinha.ca>
Message-Id: <20210812071409.492299-1-ani@anisinha.ca>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
ACPI core routines (in core.c) are not really x86-specific.
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20210616204328.2611406-21-philmd@redhat.com>
Generic code in target/arm wants to call acpi_ghes_record_errors();
provide a stub version so that we don't fail to link when
CONFIG_ACPI_APEI is not set. This requires us to add a new
ghes-stub.c file to contain it and the meson.build mechanics
to use it when appropriate.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Dongjiu Geng <gengdongjiu1@gmail.com>
Message-id: 20210603171259.27962-2-peter.maydell@linaro.org
