numa: Extend CLI to provide initiator information for numa nodes

In ACPI 6.3 chapter 5.2.27 Heterogeneous Memory Attribute Table (HMAT),
The initiator represents processor which access to memory. And in 5.2.27.3
Memory Proximity Domain Attributes Structure, the attached initiator is
defined as where the memory controller responsible for a memory proximity
domain. With attached initiator information, the topology of heterogeneous
memory can be described. Add new machine property 'hmat' to enable all
HMAT specific options.

Extend CLI of "-numa node" option to indicate the initiator numa node-id.
In the linux kernel, the codes in drivers/acpi/hmat/hmat.c parse and report
the platform's HMAT tables. Before using initiator option, enable HMAT with
-machine hmat=on.

Acked-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Jingqi Liu <jingqi.liu@intel.com>
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
Message-Id: <20191213011929.2520-2-tao3.xu@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

2 files changed, 87 insertions, 0 deletions

diff --git a/hw/core/machine.c b/hw/core/machine.c
index 0854dce..f5e2b32 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -430,6 +430,20 @@ 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);
@@ -557,6 +571,7 @@ 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;
 
@@ -626,6 +641,17 @@ 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) {
@@ -846,6 +872,13 @@ 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 */
@@ -913,6 +946,32 @@ 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;
@@ -953,6 +1012,11 @@ 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);
diff --git a/hw/core/numa.c b/hw/core/numa.c
index e3332a9..e60da99 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -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++;