[Qemu-devel] [RFC 2 PATCH 01/16] numa: Split the numa functionality

[Moger, Babu]

To support new epyc mode, we need to know the number of numa nodes
in advance to generate apic id correctly. So, split the numa
initialization into two. The function parse_numa initializes numa_info
and updates nb_numa_nodes. And then parse_numa_node does the numa node
initialization.

Signed-off-by: Babu Moger <address@hidden>
---
 hw/core/numa.c        |  106 +++++++++++++++++++++++++++++++++++--------------
 include/sysemu/numa.h |    2 +
 vl.c                  |    2 +
 3 files changed, 80 insertions(+), 30 deletions(-)

diff --git a/hw/core/numa.c b/hw/core/numa.c
index a11431483c..27fa6b5e1d 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -55,14 +55,10 @@ bool have_numa_distance;
 NodeInfo numa_info[MAX_NODES];
 
 
-static void parse_numa_node(MachineState *ms, NumaNodeOptions *node,
+static void parse_numa_info(MachineState *ms, NumaNodeOptions *node,
                             Error **errp)
 {
-    Error *err = NULL;
     uint16_t nodenr;
-    uint16List *cpus = NULL;
-    MachineClass *mc = MACHINE_GET_CLASS(ms);
-    unsigned int max_cpus = ms->smp.max_cpus;
 
     if (node->has_nodeid) {
         nodenr = node->nodeid;
@@ -81,29 +77,6 @@ static void parse_numa_node(MachineState *ms, 
NumaNodeOptions *node,
         return;
     }
 
-    if (!mc->cpu_index_to_instance_props || !mc->get_default_cpu_node_id) {
-        error_setg(errp, "NUMA is not supported by this machine-type");
-        return;
-    }
-    for (cpus = node->cpus; cpus; cpus = cpus->next) {
-        CpuInstanceProperties props;
-        if (cpus->value >= max_cpus) {
-            error_setg(errp,
-                       "CPU index (%" PRIu16 ")"
-                       " should be smaller than maxcpus (%d)",
-                       cpus->value, max_cpus);
-            return;
-        }
-        props = mc->cpu_index_to_instance_props(ms, cpus->value);
-        props.node_id = nodenr;
-        props.has_node_id = true;
-        machine_set_cpu_numa_node(ms, &props, &err);
-        if (err) {
-            error_propagate(errp, err);
-            return;
-        }
-    }
-
     have_memdevs = have_memdevs ? : node->has_memdev;
     have_mem = have_mem ? : node->has_mem;
     if ((node->has_mem && have_memdevs) || (node->has_memdev && have_mem)) {
@@ -177,7 +150,7 @@ void set_numa_options(MachineState *ms, NumaOptions 
*object, Error **errp)
 
     switch (object->type) {
     case NUMA_OPTIONS_TYPE_NODE:
-        parse_numa_node(ms, &object->u.node, &err);
+        parse_numa_info(ms, &object->u.node, &err);
         if (err) {
             goto end;
         }
@@ -242,6 +215,73 @@ end:
     return 0;
 }
 
+void set_numa_node_options(MachineState *ms, NumaOptions *object, Error **errp)
+{
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    NumaNodeOptions *node = &object->u.node;
+    unsigned int max_cpus = ms->smp.max_cpus;
+    uint16List *cpus = NULL;
+    Error *err = NULL;
+    uint16_t nodenr;
+
+    if (node->has_nodeid) {
+        nodenr = node->nodeid;
+    } else {
+        error_setg(errp, "NUMA node information is not available");
+    }
+
+    if (!mc->cpu_index_to_instance_props || !mc->get_default_cpu_node_id) {
+        error_setg(errp, "NUMA is not supported by this machine-type");
+        return;
+    }
+
+    for (cpus = node->cpus; cpus; cpus = cpus->next) {
+        CpuInstanceProperties props;
+        if (cpus->value >= max_cpus) {
+            error_setg(errp,
+                       "CPU index (%" PRIu16 ")"
+                       " should be smaller than maxcpus (%d)",
+                       cpus->value, max_cpus);
+            return;
+         }
+         props = mc->cpu_index_to_instance_props(ms, cpus->value);
+         props.node_id = nodenr;
+         props.has_node_id = true;
+         machine_set_cpu_numa_node(ms, &props, &err);
+         if (err) {
+            error_propagate(errp, err);
+            return;
+         }
+    }
+}
+
+static int parse_numa_node(void *opaque, QemuOpts *opts, Error **errp)
+{
+    NumaOptions *object = NULL;
+    MachineState *ms = MACHINE(opaque);
+    Error *err = NULL;
+    Visitor *v = opts_visitor_new(opts);
+
+    visit_type_NumaOptions(v, NULL, &object, &err);
+    visit_free(v);
+    if (err) {
+        goto end;
+    }
+
+    if (object->type == NUMA_OPTIONS_TYPE_NODE) {
+        set_numa_node_options(ms, object, &err);
+    }
+
+end:
+    qapi_free_NumaOptions(object);
+    if (err) {
+        error_propagate(errp, err);
+        return -1;
+    }
+
+    return 0;
+}
+
 /* If all node pair distances are symmetric, then only distances
  * in one direction are enough. If there is even one asymmetric
  * pair, though, then all distances must be provided. The
@@ -368,7 +408,7 @@ void numa_complete_configuration(MachineState *ms)
     if (ms->ram_slots > 0 && nb_numa_nodes == 0 &&
         mc->auto_enable_numa_with_memhp) {
             NumaNodeOptions node = { };
-            parse_numa_node(ms, &node, &error_abort);
+            parse_numa_info(ms, &node, &error_abort);
     }
 
     assert(max_numa_nodeid <= MAX_NODES);
@@ -448,6 +488,12 @@ void parse_numa_opts(MachineState *ms)
     qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, ms, &error_fatal);
 }
 
+void parse_numa_node_opts(MachineState *ms)
+{
+    qemu_opts_foreach(qemu_find_opts("numa"), parse_numa_node,
+                      ms, &error_fatal);
+}
+
 void numa_cpu_pre_plug(const CPUArchId *slot, DeviceState *dev, Error **errp)
 {
     int node_id = object_property_get_int(OBJECT(dev), "node-id", 
&error_abort);
diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 01a263eba2..ca109adaa6 100644
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -24,7 +24,9 @@ struct NumaNodeMem {
 extern NodeInfo numa_info[MAX_NODES];
 
 void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp);
+void set_numa_node_options(MachineState *ms, NumaOptions *object, Error 
**errp);
 void parse_numa_opts(MachineState *ms);
+void parse_numa_node_opts(MachineState *ms);
 void numa_complete_configuration(MachineState *ms);
 void query_numa_node_mem(NumaNodeMem node_mem[]);
 extern QemuOptsList qemu_numa_opts;
diff --git a/vl.c b/vl.c
index b426b32134..711d2ae5da 100644
--- a/vl.c
+++ b/vl.c
@@ -4339,6 +4339,8 @@ int main(int argc, char **argv, char **envp)
     }
     parse_numa_opts(current_machine);
 
+    parse_numa_node_opts(current_machine);
+
     /* do monitor/qmp handling at preconfig state if requested */
     main_loop();