qemu-devel
[Top][All Lists]
Advanced

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

Re: [PATCH v1 3/4] hw/arm/virt-acpi-build: patch guest SRAT for NUMA nod


From: Igor Mammedov
Subject: Re: [PATCH v1 3/4] hw/arm/virt-acpi-build: patch guest SRAT for NUMA nodes
Date: Fri, 15 Sep 2023 16:52:51 +0200

On Thu, 14 Sep 2023 19:45:58 -0700
<ankita@nvidia.com> wrote:

> From: Ankit Agrawal <ankita@nvidia.com>
> 
> During bootup, Linux kernel parse the ACPI SRAT to determine the PXM ids.
> This allows for the creation of NUMA nodes for each unique id.
> 
> Insert a series of the unique PXM ids in the VM SRAT ACPI table. The
> range of nodes can be determined from the "dev_mem_pxm_start" and
> "dev_mem_pxm_count" object properties associated with the device. These
> nodes as made MEM_AFFINITY_HOTPLUGGABLE. This allows the kernel to create
> memory-less NUMA nodes on bootup to which a subrange (or entire range) of
> device memory can be added/removed.

QEMU already has 'memory devices'. perhaps this case belongs to the same class
CCing David.

> 
> Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
> ---
>  hw/arm/virt-acpi-build.c | 54 ++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 54 insertions(+)
> 
> diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
> index 6b674231c2..6d1e3b6b8a 100644
> --- a/hw/arm/virt-acpi-build.c
> +++ b/hw/arm/virt-acpi-build.c
> @@ -46,6 +46,7 @@
>  #include "hw/acpi/hmat.h"
>  #include "hw/pci/pcie_host.h"
>  #include "hw/pci/pci.h"
> +#include "hw/vfio/pci.h"
>  #include "hw/pci/pci_bus.h"
>  #include "hw/pci-host/gpex.h"
>  #include "hw/arm/virt.h"
> @@ -515,6 +516,57 @@ build_spcr(GArray *table_data, BIOSLinker *linker, 
> VirtMachineState *vms)
>      acpi_table_end(linker, &table);
>  }
>  
> +static int devmem_device_list(Object *obj, void *opaque)
> +{
> +    GSList **list = opaque;
> +
> +    if (object_dynamic_cast(obj, TYPE_VFIO_PCI)) {
> +        *list = g_slist_append(*list, DEVICE(obj));
> +    }
> +
> +    object_child_foreach(obj, devmem_device_list, opaque);
> +    return 0;
> +}
> +
> +static GSList *devmem_get_device_list(void)
> +{
> +    GSList *list = NULL;
> +
> +    object_child_foreach(qdev_get_machine(), devmem_device_list, &list);
> +    return list;
> +}
> +
> +static void build_srat_devmem(GArray *table_data)
> +{
> +    GSList *device_list, *list = devmem_get_device_list();
> +
> +    for (device_list = list; device_list; device_list = device_list->next) {
> +        DeviceState *dev = device_list->data;
> +        Object *obj = OBJECT(dev);
> +        VFIOPCIDevice *pcidev
> +            = ((VFIOPCIDevice *)object_dynamic_cast(OBJECT(obj),
> +               TYPE_VFIO_PCI));
> +
> +        if (pcidev->pdev.has_coherent_memory) {
> +            uint64_t start_node = object_property_get_uint(obj,
> +                                  "dev_mem_pxm_start", &error_abort);
> +            uint64_t node_count = object_property_get_uint(obj,
> +                                  "dev_mem_pxm_count", &error_abort);
> +            uint64_t node_index;
> +
> +            /*
> +             * Add the node_count PXM domains starting from start_node as
> +             * hot pluggable. The VM kernel parse the PXM domains and
> +             * creates NUMA nodes.
> +             */
> +            for (node_index = 0; node_index < node_count; node_index++)
> +                build_srat_memory(table_data, 0, 0, start_node + node_index,
> +                    MEM_AFFINITY_ENABLED | MEM_AFFINITY_HOTPLUGGABLE);
> +        }
> +    }
> +    g_slist_free(list);
> +}
> +
>  /*
>   * ACPI spec, Revision 5.1
>   * 5.2.16 System Resource Affinity Table (SRAT)
> @@ -569,6 +621,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, 
> VirtMachineState *vms)
>                            MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
>      }
>  
> +    build_srat_devmem(table_data);
> +
>      acpi_table_end(linker, &table);
>  }
>  




reply via email to

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