The empty NUMA nodes, where no memory resides, aren't exposed
through ACPI SRAT table. It's not user preferred behaviour because
the corresponding memory node devices are missed from the guest
kernel as the following example shows. It means the guest kernel
doesn't have the node information as user specifies. However,
memory can be still hot added to these empty NUMA nodes when
they're not exposed.
/home/gavin/sandbox/qemu.main/build/qemu-system-aarch64 \
-accel kvm -machine virt,gic-version=host \
-cpu host -smp 4,sockets=2,cores=2,threads=1 \
-m 1024M,slots=16,maxmem=64G \
-object memory-backend-ram,id=mem0,size=512M \
-object memory-backend-ram,id=mem1,size=512M \
-numa node,nodeid=0,cpus=0-1,memdev=mem0 \
-numa node,nodeid=1,cpus=2-3,memdev=mem1 \
-numa node,nodeid=2 \
-numa node,nodeid=3 \
:
guest# ls /sys/devices/system/node | grep node
node0
node1
(qemu) object_add memory-backend-ram,id=hp-mem0,size=1G
(qemu) device_add pc-dimm,id=hp-dimm0,node=3,memdev=hp-mem0
guest# ls /sys/devices/system/node | grep node
node0
node1
node2
guest# cat /sys/devices/system/node/node2/meminfo | grep MemTotal
Node 2 MemTotal: 1048576 kB
This exposes these empty NUMA nodes through ACPI SRAT table. With
this applied, the corresponding memory node devices can be found
from the guest. Note that the hotpluggable capability is explicitly
given to these empty NUMA nodes for sake of completeness.
guest# ls /sys/devices/system/node | grep node
node0
node1
node2
node3
guest# cat /sys/devices/system/node/node3/meminfo | grep MemTotal
Node 3 MemTotal: 0 kB
(qemu) object_add memory-backend-ram,id=hp-mem0,size=1G
(qemu) device_add pc-dimm,id=hp-dimm0,node=3,memdev=hp-mem0
guest# cat /sys/devices/system/node/node3/meminfo | grep MemTotal
Node 3 MemTotal: 1048576 kB
Signed-off-by: Gavin Shan <[email protected]>
Reviewed-by: Andrew Jones <[email protected]>
---
v2: Improved commit log as suggested by Drew and Igor.
---
hw/arm/virt-acpi-build.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 674f902652..a4c95b2f64 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -526,6 +526,7 @@ build_srat(GArray *table_data, BIOSLinker *linker,
VirtMachineState *vms)
const CPUArchIdList *cpu_list = mc->possible_cpu_arch_ids(ms);
AcpiTable table = { .sig = "SRAT", .rev = 3, .oem_id = vms->oem_id,
.oem_table_id = vms->oem_table_id };
+ MemoryAffinityFlags flags;
acpi_table_begin(&table, table_data);
build_append_int_noprefix(table_data, 1, 4); /* Reserved */
@@ -547,12 +548,15 @@ build_srat(GArray *table_data, BIOSLinker *linker,
VirtMachineState *vms)
mem_base = vms->memmap[VIRT_MEM].base;
for (i = 0; i < ms->numa_state->num_nodes; ++i) {
- if (ms->numa_state->nodes[i].node_mem > 0) {
- build_srat_memory(table_data, mem_base,
- ms->numa_state->nodes[i].node_mem, i,
- MEM_AFFINITY_ENABLED);
- mem_base += ms->numa_state->nodes[i].node_mem;
+ if (ms->numa_state->nodes[i].node_mem) {
+ flags = MEM_AFFINITY_ENABLED;
+ } else {
+ flags = MEM_AFFINITY_ENABLED | MEM_AFFINITY_HOTPLUGGABLE;
}
+
+ build_srat_memory(table_data, mem_base,
+ ms->numa_state->nodes[i].node_mem, i, flags);
+ mem_base += ms->numa_state->nodes[i].node_mem;
}
if (ms->nvdimms_state->is_enabled) {
--
2.23.0
