[PATCH v3 1/2] numa: Require distance map when empty node exists

[Gavin Shan]

The following option is used to specify the distance map. It's
possible the option isn't provided by user. In this case, the
distance map isn't populated and exposed to platform. On the
other hand, the empty NUMA node, where no memory resides, is
allowed on platforms like ARM64 virt. For these empty NUMA
nodes, their corresponding device-tree nodes aren't populated,
but their NUMA IDs should be included in the "/distance-map"
device-tree node, so that kernel can probe them properly if
device-tree is used.

  -numa,dist,src=<numa_id>,dst=<numa_id>,val=<distance>

This adds extra check after the machine is initialized, to
ask for the distance map from user when empty nodes exist in
device-tree.

Signed-off-by: Gavin Shan <gshan@redhat.com>
---
 hw/core/machine.c     |  4 ++++
 hw/core/numa.c        | 24 ++++++++++++++++++++++++
 include/sysemu/numa.h |  1 +
 3 files changed, 29 insertions(+)

diff --git a/hw/core/machine.c b/hw/core/machine.c
index b8d95eec32..c0765ad973 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -1355,6 +1355,10 @@ void machine_run_board_init(MachineState *machine)
     accel_init_interfaces(ACCEL_GET_CLASS(machine->accelerator));
     machine_class->init(machine);
     phase_advance(PHASE_MACHINE_INITIALIZED);
+
+    if (machine->numa_state) {
+        numa_complete_validation(machine);
+    }
 }
 
 static NotifierList machine_init_done_notifiers =
diff --git a/hw/core/numa.c b/hw/core/numa.c
index 510d096a88..7404b7dd38 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -727,6 +727,30 @@ void numa_complete_configuration(MachineState *ms)
     }
 }
 
+/*
+ * When device-tree is used by the machine, the empty node IDs should
+ * be included in the distance map. So we need provide pairs of distances
+ * in this case.
+ */
+void numa_complete_validation(MachineState *ms)
+{
+    NodeInfo *numa_info = ms->numa_state->nodes;
+    int nb_numa_nodes = ms->numa_state->num_nodes;
+    int i;
+
+    if (!ms->fdt || ms->numa_state->have_numa_distance) {
+        return;
+    }
+
+    for (i = 0; i < nb_numa_nodes; i++) {
+        if (numa_info[i].present && !numa_info[i].node_mem) {
+            error_report("Empty node %d found, please provide "
+                         "distance map.", i);
+            exit(EXIT_FAILURE);
+        }
+    }
+}
+
 void parse_numa_opts(MachineState *ms)
 {
     qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, ms, &error_fatal);
diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 4173ef2afa..80f25ab830 100644
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -104,6 +104,7 @@ void parse_numa_hmat_lb(NumaState *numa_state, 
NumaHmatLBOptions *node,
 void parse_numa_hmat_cache(MachineState *ms, NumaHmatCacheOptions *node,
                            Error **errp);
 void numa_complete_configuration(MachineState *ms);
+void numa_complete_validation(MachineState *ms);
 void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms);
 extern QemuOptsList qemu_numa_opts;
 void numa_cpu_pre_plug(const struct CPUArchId *slot, DeviceState *dev,
-- 
2.23.0