[Qemu-devel] [PATCH v6 05/14] numa: Extend CLI to provide initiator information for numa nodes

[Tao Xu <tao3.xu@intel.com>]

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.

Extend CLI of "-numa node" option to indicate the initiator numa
node-id.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
---
 hw/core/machine.c     | 24 ++++++++++++++++++++++++
 include/sysemu/numa.h |  3 +++
 numa.c                | 13 +++++++++++++
 qapi/misc.json        |  6 +++++-
 qemu-options.hx       | 27 +++++++++++++++++++++++----
 5 files changed, 68 insertions(+), 5 deletions(-)

diff --git a/hw/core/machine.c b/hw/core/machine.c
index 77b5967a68..c48e5b8078 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -649,6 +649,7 @@ 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;
 
@@ -709,6 +710,16 @@ 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 (numa_info[props->node_id].initiator_valid &&
+            (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].initiator_valid = true;
+        numa_info[props->node_id].has_cpu = true;
+        numa_info[props->node_id].initiator = props->node_id;
     }
 
     if (!match) {
@@ -974,6 +985,7 @@ static void machine_numa_finish_cpu_init(MachineState *machine)
     GString *s = g_string_new(NULL);
     MachineClass *mc = MACHINE_GET_CLASS(machine);
     const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(machine);
+    NodeInfo *numa_info = machine->numa_state->nodes;
 
     assert(machine->numa_state->num_nodes);
     for (i = 0; i < possible_cpus->len; i++) {
@@ -1007,6 +1019,18 @@ static void machine_numa_finish_cpu_init(MachineState *machine)
             machine_set_cpu_numa_node(machine, &props, &error_fatal);
         }
     }
+
+    for (i = 0; i < machine->numa_state->num_nodes; i++) {
+        if (numa_info[i].initiator_valid &&
+            !numa_info[numa_info[i].initiator].has_cpu) {
+            error_report("The initiator-id %"PRIu16 " of NUMA node %d"
+                         " does not exist.", numa_info[i].initiator, i);
+            error_printf("\n");
+
+            exit(1);
+        }
+    }
+
     if (s->len && !qtest_enabled()) {
         warn_report("CPU(s) not present in any NUMA nodes: %s",
                     s->str);
diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 957ad60560..357aaeda80 100644
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -10,6 +10,9 @@ struct NodeInfo {
     uint64_t node_mem;
     struct HostMemoryBackend *node_memdev;
     bool present;
+    bool has_cpu;
+    bool initiator_valid;
+    uint16_t initiator;
     uint8_t distance[MAX_NODES];
 };
 
diff --git a/numa.c b/numa.c
index 850c7f4573..4a3a1726be 100644
--- a/numa.c
+++ b/numa.c
@@ -131,6 +131,19 @@ 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 (node->has_initiator) {
+        if (numa_info[nodenr].initiator_valid &&
+            (node->initiator != numa_info[nodenr].initiator)) {
+            error_setg(errp, "The initiator of NUMA node %" PRIu16 " has been "
+                       "set to node %" PRIu16, nodenr,
+                       numa_info[nodenr].initiator);
+            return;
+        }
+
+        numa_info[nodenr].initiator_valid = true;
+        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++;
diff --git a/qapi/misc.json b/qapi/misc.json
index dc4cf9da20..3059bb3119 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -2572,6 +2572,9 @@
 # @memdev: memory backend object.  If specified for one node,
 #          it must be specified for all nodes.
 #
+# @initiator: the initiator numa nodeid that is closest (as in directly
+#             attached) to this numa node.
+#
 # Since: 2.1
 ##
 { 'struct': 'NumaNodeOptions',
@@ -2579,7 +2582,8 @@
    '*nodeid': 'uint16',
    '*cpus':   ['uint16'],
    '*mem':    'size',
-   '*memdev': 'str' }}
+   '*memdev': 'str',
+   '*initiator': 'uint16' }}
 
 ##
 # @NumaDistOptions:
diff --git a/qemu-options.hx b/qemu-options.hx
index c18b79099a..e6f5da469d 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -160,14 +160,14 @@ specifies the maximum number of hotpluggable CPUs.
 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
@@ -214,6 +214,25 @@ 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} indicate the initiator NUMA @var{initiator} that is
+closest (as in directly attached) to this NUMA @var{node}.
+
+For example, the following option assigns 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
+-M pc \
+-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
-- 
2.20.1