On Tue, 16 Jun 2026 17:08:05 +0800 fanhuang <[email protected]> wrote:
> Introduce a TYPE_MEMORY_DEVICE subclass `sp-mem` for boot-time > SOFT_RESERVED memory exposed to the guest with a per-device NUMA > proximity domain. > > The device targets accelerator memory (HBM and similar) that the > firmware hands to the guest OS as SOFT_RESERVED memory, so a driver > in the guest -- rather than the kernel's general allocator -- owns > the range. > > Usage: > > -object memory-backend-ram,id=spm0,size=$SIZE > -numa node,nodeid=$N > -device sp-mem,id=dev0,memdev=spm0,node=$N[,addr=$GPA] > > The device is boot-time only (no hotplug). Modulo nitpicking/patch splitting and a migration question LGTM > > Signed-off-by: FangSheng Huang <[email protected]> > --- > qapi/machine.json | 43 +++++++++++- > include/hw/mem/sp-mem.h | 33 +++++++++ > hw/core/machine-hmp-cmds.c | 11 +++ > hw/mem/sp-mem.c | 136 +++++++++++++++++++++++++++++++++++++ > hw/mem/Kconfig | 4 ++ > hw/mem/meson.build | 1 + > 6 files changed, 226 insertions(+), 2 deletions(-) > create mode 100644 include/hw/mem/sp-mem.h > create mode 100644 hw/mem/sp-mem.c > > diff --git a/qapi/machine.json b/qapi/machine.json > index 685e4e29b8..777cfc81e1 100644 > --- a/qapi/machine.json > +++ b/qapi/machine.json > @@ -1413,6 +1413,32 @@ > } > } > > +## > +# @SpMemDeviceInfo: > +# > +# sp-mem device state information > +# > +# @id: device's ID > +# > +# @addr: physical address, where device is mapped > +# > +# @size: size of memory that the device provides > +# > +# @node: NUMA proximity domain to which the device is assigned > +# > +# @memdev: memory backend linked with device > +# > +# Since: 11.1 > +## > +{ 'struct': 'SpMemDeviceInfo', > + 'data': { '*id': 'str', > + 'addr': 'size', > + 'size': 'size', > + 'node': 'int', > + 'memdev': 'str' > + } > +} > + > ## > # @MemoryDeviceInfoKind: > # > @@ -1426,11 +1452,13 @@ > # > # @hv-balloon: since 8.2. > # > +# @sp-mem: since 11.1. > +# > # Since: 2.1 > ## > { 'enum': 'MemoryDeviceInfoKind', > 'data': [ 'dimm', 'nvdimm', 'virtio-pmem', 'virtio-mem', 'sgx-epc', > - 'hv-balloon' ] } > + 'hv-balloon', 'sp-mem' ] } > > ## > # @PCDIMMDeviceInfoWrapper: > @@ -1482,6 +1510,16 @@ > { 'struct': 'HvBalloonDeviceInfoWrapper', > 'data': { 'data': 'HvBalloonDeviceInfo' } } > > +## > +# @SpMemDeviceInfoWrapper: > +# > +# @data: sp-mem device state information > +# > +# Since: 11.1 > +## > +{ 'struct': 'SpMemDeviceInfoWrapper', > + 'data': { 'data': 'SpMemDeviceInfo' } } > + > ## > # @MemoryDeviceInfo: > # > @@ -1499,7 +1537,8 @@ > 'virtio-pmem': 'VirtioPMEMDeviceInfoWrapper', > 'virtio-mem': 'VirtioMEMDeviceInfoWrapper', > 'sgx-epc': 'SgxEPCDeviceInfoWrapper', > - 'hv-balloon': 'HvBalloonDeviceInfoWrapper' > + 'hv-balloon': 'HvBalloonDeviceInfoWrapper', > + 'sp-mem': 'SpMemDeviceInfoWrapper' > } > } > > diff --git a/include/hw/mem/sp-mem.h b/include/hw/mem/sp-mem.h > new file mode 100644 > index 0000000000..a8951b49e6 > --- /dev/null > +++ b/include/hw/mem/sp-mem.h > @@ -0,0 +1,33 @@ > +/* > + * Specific Purpose Memory (SPM) device > + * > + * TYPE_MEMORY_DEVICE subclass for boot-time-only memory exposed to the > + * guest as an E820 SOFT_RESERVED range with a SRAT memory-affinity entry. > + * > + * Copyright (c) 2026 Advanced Micro Devices, Inc. > + * > + * Authors: > + * FangSheng Huang <[email protected]> > + * > + * SPDX-License-Identifier: GPL-2.0-or-later > + */ > + > +#ifndef QEMU_SP_MEM_H > +#define QEMU_SP_MEM_H > + > +#include "hw/core/qdev.h" > +#include "qom/object.h" > + > +#define TYPE_SP_MEM "sp-mem" > + > +OBJECT_DECLARE_SIMPLE_TYPE(SpMemDevice, SP_MEM) > + > +struct SpMemDevice { > + DeviceState parent_obj; > + > + HostMemoryBackend *hostmem; > + uint32_t node; > + uint64_t addr; > +}; > + > +#endif /* QEMU_SP_MEM_H */ > diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c > index 46846f741a..686304bafa 100644 > --- a/hw/core/machine-hmp-cmds.c > +++ b/hw/core/machine-hmp-cmds.c > @@ -279,6 +279,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict > *qdict) > PCDIMMDeviceInfo *di; > SgxEPCDeviceInfo *se; > HvBalloonDeviceInfo *hi; > + SpMemDeviceInfo *spmi; > > for (info = info_list; info; info = info->next) { > value = info->value; > @@ -350,6 +351,16 @@ void hmp_info_memory_devices(Monitor *mon, const QDict > *qdict) > monitor_printf(mon, " memdev: %s\n", hi->memdev); > } > break; > + case MEMORY_DEVICE_INFO_KIND_SP_MEM: > + spmi = value->u.sp_mem.data; > + monitor_printf(mon, "Memory device [%s]: \"%s\"\n", > + MemoryDeviceInfoKind_str(value->type), > + spmi->id ? spmi->id : ""); > + monitor_printf(mon, " addr: 0x%" PRIx64 "\n", spmi->addr); > + monitor_printf(mon, " node: %" PRId64 "\n", spmi->node); > + monitor_printf(mon, " size: %" PRIu64 "\n", spmi->size); > + monitor_printf(mon, " memdev: %s\n", spmi->memdev); > + break; > default: > g_assert_not_reached(); > } hmp could be a separate patch. > diff --git a/hw/mem/sp-mem.c b/hw/mem/sp-mem.c > new file mode 100644 > index 0000000000..3b46cabc46 > --- /dev/null > +++ b/hw/mem/sp-mem.c > @@ -0,0 +1,136 @@ > +/* > + * Specific Purpose Memory (SPM) device > + * > + * Copyright (c) 2026 Advanced Micro Devices, Inc. > + * > + * Authors: > + * FangSheng Huang <[email protected]> > + * > + * SPDX-License-Identifier: GPL-2.0-or-later > + */ > + > +#include "qemu/osdep.h" > +#include "qemu/module.h" > +#include "qapi/error.h" > +#include "hw/core/qdev-properties.h" > +#include "hw/core/qdev.h" > +#include "hw/mem/sp-mem.h" > +#include "hw/mem/memory-device.h" > +#include "migration/vmstate.h" > +#include "system/hostmem.h" > + > +#define SP_MEM_MEMDEV_PROP "memdev" > +#define SP_MEM_NODE_PROP "node" > +#define SP_MEM_ADDR_PROP "addr" > + > +static const Property sp_mem_properties[] = { > + DEFINE_PROP_LINK(SP_MEM_MEMDEV_PROP, SpMemDevice, hostmem, > + TYPE_MEMORY_BACKEND, HostMemoryBackend *), > + DEFINE_PROP_UINT32(SP_MEM_NODE_PROP, SpMemDevice, node, 0), > + DEFINE_PROP_UINT64(SP_MEM_ADDR_PROP, SpMemDevice, addr, 0), > +}; > + > +static uint64_t sp_mem_get_addr(const MemoryDeviceState *md) > +{ > + return object_property_get_uint(OBJECT(md), SP_MEM_ADDR_PROP, > + &error_abort); > +} > + > +static void sp_mem_set_addr(MemoryDeviceState *md, uint64_t addr, > + Error **errp) > +{ > + object_property_set_uint(OBJECT(md), SP_MEM_ADDR_PROP, addr, errp); > +} > + > +static MemoryRegion *sp_mem_get_memory_region(MemoryDeviceState *md, > + Error **errp) > +{ > + SpMemDevice *spm = SP_MEM(md); > + > + if (!spm->hostmem) { > + error_setg(errp, "'%s' property must be set", SP_MEM_MEMDEV_PROP); > + return NULL; > + } > + return host_memory_backend_get_memory(spm->hostmem); > +} > + > +static void sp_mem_fill_device_info(const MemoryDeviceState *md, > + MemoryDeviceInfo *info) > +{ > + SpMemDeviceInfo *di = g_new0(SpMemDeviceInfo, 1); > + SpMemDevice *spm = SP_MEM(md); > + DeviceState *dev = DEVICE(md); > + > + di->id = dev->id ? g_strdup(dev->id) : NULL; > + di->addr = spm->addr; > + di->size = memory_region_size( > + host_memory_backend_get_memory(spm->hostmem)); > + di->node = spm->node; > + di->memdev = object_get_canonical_path(OBJECT(spm->hostmem)); > + > + info->u.sp_mem.data = di; > + info->type = MEMORY_DEVICE_INFO_KIND_SP_MEM; > +} if missing this doesn't break anything, I'd bundle it together with hmp patch > + > +static void sp_mem_realize(DeviceState *dev, Error **errp) > +{ > + SpMemDevice *spm = SP_MEM(dev); > + > + if (!spm->hostmem) { > + error_setg(errp, "'%s' property is required", SP_MEM_MEMDEV_PROP); > + return; > + } > + if (host_memory_backend_is_mapped(spm->hostmem)) { > + error_setg(errp, "memory backend '%s' is already in use", > + > object_get_canonical_path_component(OBJECT(spm->hostmem))); > + return; > + } > + host_memory_backend_set_mapped(spm->hostmem, true); > +} > + > +static void sp_mem_unrealize(DeviceState *dev) > +{ > + SpMemDevice *spm = SP_MEM(dev); > + > + host_memory_backend_set_mapped(spm->hostmem, false); > +} > + > +static const VMStateDescription vmstate_sp_mem = { > + .name = TYPE_SP_MEM, > + /* boot-time only; no plug/unplug state to migrate */ > + .unmigratable = 1, this is explicit migration blocker, isn't it? are we sure about setting it un-migratable, if yes/no than why? I don't see how plug/unplug is involved here, but I'd speculate that we would want to migrate memory content itself. CCing Peter, for a look from migration pov > +}; > + > +static void sp_mem_class_init(ObjectClass *oc, const void *data) > +{ > + DeviceClass *dc = DEVICE_CLASS(oc); > + MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(oc); > + > + dc->desc = "SPM (Specific Purpose Memory) device"; > + dc->hotpluggable = false; > + dc->realize = sp_mem_realize; > + dc->unrealize = sp_mem_unrealize; > + dc->vmsd = &vmstate_sp_mem; > + device_class_set_props(dc, sp_mem_properties); > + > + mdc->get_addr = sp_mem_get_addr; > + mdc->set_addr = sp_mem_set_addr; > + mdc->get_memory_region = sp_mem_get_memory_region; > + mdc->get_plugged_size = memory_device_get_region_size; > + mdc->fill_device_info = sp_mem_fill_device_info; > +} > + > +static const TypeInfo sp_mem_types[] = { > + { > + .name = TYPE_SP_MEM, > + .parent = TYPE_DEVICE, > + .class_init = sp_mem_class_init, > + .instance_size = sizeof(SpMemDevice), > + .interfaces = (InterfaceInfo[]) { > + { TYPE_MEMORY_DEVICE }, > + { } > + }, > + }, > +}; > + > +DEFINE_TYPES(sp_mem_types) > diff --git a/hw/mem/Kconfig b/hw/mem/Kconfig > index 73c5ae8ad9..39ddb36710 100644 > --- a/hw/mem/Kconfig > +++ b/hw/mem/Kconfig > @@ -16,3 +16,7 @@ config CXL_MEM_DEVICE > bool > default y if CXL > select MEM_DEVICE > + > +config SP_MEM > + bool > + select MEM_DEVICE > diff --git a/hw/mem/meson.build b/hw/mem/meson.build > index 8c2beeb7d4..f410d75475 100644 > --- a/hw/mem/meson.build > +++ b/hw/mem/meson.build > @@ -4,6 +4,7 @@ mem_ss.add(when: 'CONFIG_DIMM', if_true: files('pc-dimm.c')) > mem_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_mc.c')) > mem_ss.add(when: 'CONFIG_NVDIMM', if_true: files('nvdimm.c')) > mem_ss.add(when: 'CONFIG_CXL_MEM_DEVICE', if_true: files('cxl_type3.c')) > +mem_ss.add(when: 'CONFIG_SP_MEM', if_true: files('sp-mem.c')) > stub_ss.add(files('cxl_type3_stubs.c')) > > stub_ss.add(files('memory-device-stubs.c'))
