@@ -518,6 +518,20 @@ static void machine_set_nvdimm(Object *obj, bool value, Error **errp)
ms->nvdimms_state->is_enabled = value;
}
+static bool machine_get_hmat(Object *obj, Error **errp)
+{
+ MachineState *ms = MACHINE(obj);
+
+ return ms->numa_state->hmat_enabled;
+}
+
+static void machine_set_hmat(Object *obj, bool value, Error **errp)
+{
+ MachineState *ms = MACHINE(obj);
+
+ ms->numa_state->hmat_enabled = value;
+}
+
static char *machine_get_nvdimm_persistence(Object *obj, Error **errp)
{
MachineState *ms = MACHINE(obj);
@@ -645,6 +659,7 @@ void machine_set_cpu_numa_node(MachineState *machine,
const CpuInstanceProperties *props, Error **errp)
{
MachineClass *mc = MACHINE_GET_CLASS(machine);
+ NodeInfo *numa_info = machine->numa_state->nodes;
bool match = false;
int i;
@@ -714,6 +729,17 @@ void machine_set_cpu_numa_node(MachineState *machine,
match = true;
slot->props.node_id = props->node_id;
slot->props.has_node_id = props->has_node_id;
+
+ if (machine->numa_state->hmat_enabled) {
+ if ((numa_info[props->node_id].initiator < MAX_NODES) &&
+ (props->node_id != numa_info[props->node_id].initiator)) {
+ error_setg(errp, "The initiator of CPU NUMA node %" PRId64
+ " should be itself.", props->node_id);
+ return;
+ }
+ numa_info[props->node_id].has_cpu = true;
+ numa_info[props->node_id].initiator = props->node_id;
+ }
}
if (!match) {
@@ -960,6 +986,13 @@ static void machine_initfn(Object *obj)
if (mc->numa_mem_supported) {
ms->numa_state = g_new0(NumaState, 1);
+ object_property_add_bool(obj, "hmat",
+ machine_get_hmat, machine_set_hmat,
+ &error_abort);
+ object_property_set_description(obj, "hmat",
+ "Set on/off to enable/disable "
+ "ACPI Heterogeneous Memory Attribute "
+ "Table (HMAT)", NULL);
}
/* Register notifier when init is done for sysbus sanity checks */
@@ -1048,6 +1081,32 @@ static char *cpu_slot_to_string(const CPUArchId *cpu)
return g_string_free(s, false);
}
+static void numa_validate_initiator(NumaState *numa_state)
+{
+ int i;
+ NodeInfo *numa_info = numa_state->nodes;
+
+ for (i = 0; i < numa_state->num_nodes; i++) {
+ if (numa_info[i].initiator == MAX_NODES) {
+ error_report("The initiator of NUMA node %d is missing, use "
+ "'-numa node,initiator' option to declare it.", i);
+ exit(1);
+ }
+
+ if (!numa_info[numa_info[i].initiator].present) {
+ error_report("NUMA node %" PRIu16 " is missing, use "
+ "'-numa node' option to declare it first.",
+ numa_info[i].initiator);
+ exit(1);
+ }
+
+ if (!numa_info[numa_info[i].initiator].has_cpu) {
+ error_report("The initiator of NUMA node %d is invalid.", i);
+ exit(1);
+ }
+ }
+}
+
static void machine_numa_finish_cpu_init(MachineState *machine)
{
int i;
@@ -1088,6 +1147,11 @@ static void machine_numa_finish_cpu_init(MachineState *machine)
machine_set_cpu_numa_node(machine, &props, &error_fatal);
}
}
+
+ if (machine->numa_state->hmat_enabled) {
+ numa_validate_initiator(machine->numa_state);
+ }
+
if (s->len && !qtest_enabled()) {
warn_report("CPU(s) not present in any NUMA nodes: %s",
s->str);
@@ -133,6 +133,29 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node,
numa_info[nodenr].node_mem = object_property_get_uint(o, "size", NULL);
numa_info[nodenr].node_memdev = MEMORY_BACKEND(o);
}
+
+ /*
+ * If not set the initiator, set it to MAX_NODES. And if
+ * HMAT is enabled and this node has no cpus, QEMU will raise error.
+ */
+ numa_info[nodenr].initiator = MAX_NODES;
+ if (node->has_initiator) {
+ if (!ms->numa_state->hmat_enabled) {
+ error_setg(errp, "ACPI Heterogeneous Memory Attribute Table "
+ "(HMAT) is disabled, enable it with -machine hmat=on "
+ "before using any of hmat specific options.");
+ return;
+ }
+
+ if (node->initiator >= MAX_NODES) {
+ error_report("The initiator id %" PRIu16 " expects an integer "
+ "between 0 and %d", node->initiator,
+ MAX_NODES - 1);
+ return;
+ }
+
+ numa_info[nodenr].initiator = node->initiator;
+ }
numa_info[nodenr].present = true;
max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1);
ms->numa_state->num_nodes++;
@@ -18,6 +18,8 @@ struct NodeInfo {
uint64_t node_mem;
struct HostMemoryBackend *node_memdev;
bool present;
+ bool has_cpu;
+ uint16_t initiator;
uint8_t distance[MAX_NODES];
};
@@ -33,6 +35,9 @@ struct NumaState {
/* Allow setting NUMA distance for different NUMA nodes */
bool have_numa_distance;
+ /* Detect if HMAT support is enabled. */
+ bool hmat_enabled;
+
/* NUMA nodes information */
NodeInfo nodes[MAX_NODES];
};
@@ -463,6 +463,13 @@
# @memdev: memory backend object. If specified for one node,
# it must be specified for all nodes.
#
+# @initiator: defined in ACPI 6.3 Chapter 5.2.27.3 Table 5-145,
+# points to the nodeid which has the memory controller
+# responsible for this NUMA node. This field provides
+# additional information as to the initiator node that
+# is closest (as in directly attached) to this node, and
+# therefore has the best performance (since 5.0)
+#
# Since: 2.1
##
{ 'struct': 'NumaNodeOptions',
@@ -470,7 +477,8 @@
'*nodeid': 'uint16',
'*cpus': ['uint16'],
'*mem': 'size',
- '*memdev': 'str' }}
+ '*memdev': 'str',
+ '*initiator': 'uint16' }}
##
# @NumaDistOptions:
@@ -43,7 +43,8 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \
" suppress-vmdesc=on|off disables self-describing migration (default=off)\n"
" nvdimm=on|off controls NVDIMM support (default=off)\n"
" enforce-config-section=on|off enforce configuration section migration (default=off)\n"
- " memory-encryption=@var{} memory encryption object to use (default=none)\n",
+ " memory-encryption=@var{} memory encryption object to use (default=none)\n"
+ " hmat=on|off controls ACPI HMAT support (default=off)\n",
QEMU_ARCH_ALL)
STEXI
@item -machine [type=]@var{name}[,prop=@var{value}[,...]]
@@ -103,6 +104,9 @@ NOTE: this parameter is deprecated. Please use @option{-global}
@option{migration.send-configuration}=@var{on|off} instead.
@item memory-encryption=@var{}
Memory encryption object to use. The default is none.
+@item hmat=on|off
+Enables or disables ACPI Heterogeneous Memory Attribute Table (HMAT) support.
+The default is off.
@end table
ETEXI
@@ -161,14 +165,14 @@ If any on the three values is given, the total number of CPUs @var{n} can be omi
ETEXI
DEF("numa", HAS_ARG, QEMU_OPTION_numa,
- "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node]\n"
- "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node]\n"
+ "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n"
+ "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n"
"-numa dist,src=source,dst=destination,val=distance\n"
"-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n",
QEMU_ARCH_ALL)
STEXI
-@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}]
-@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}]
+@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}]
+@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}]
@itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance}
@itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}]
@findex -numa
@@ -215,6 +219,27 @@ split equally between them.
@samp{mem} and @samp{memdev} are mutually exclusive. Furthermore,
if one node uses @samp{memdev}, all of them have to use it.
+@samp{initiator} is an additional option that points to an @var{initiator}
+NUMA node that has best performance (the lowest latency or largest bandwidth)
+to this NUMA @var{node}. Note that this option can be set only when
+the machine property 'hmat' is set to 'on'.
+
+Following example creates a machine with 2 NUMA nodes, node 0 has CPU.
+node 1 has only memory, and its initiator is node 0. Note that because
+node 0 has CPU, by default the initiator of node 0 is itself and must be
+itself.
+@example
+-machine hmat=on \
+-m 2G,slots=2,maxmem=4G \
+-object memory-backend-ram,size=1G,id=m0 \
+-object memory-backend-ram,size=1G,id=m1 \
+-numa node,nodeid=0,memdev=m0 \
+-numa node,nodeid=1,memdev=m1,initiator=0 \
+-smp 2,sockets=2,maxcpus=2 \
+-numa cpu,node-id=0,socket-id=0 \
+-numa cpu,node-id=0,socket-id=1
+@end example
+
@var{source} and @var{destination} are NUMA node IDs.
@var{distance} is the NUMA distance from @var{source} to @var{destination}.
The distance from a node to itself is always 10. If any pair of nodes is