qom/cpu: Add cluster_index to CPUState

For TCG we want to distinguish which cluster a CPU is in, and
we need to do it quickly. Cache the cluster index in the CPUState
struct, by having the cluster object set cpu->cluster_index for
each CPU child when it is realized.

This means that board/SoC code must add all CPUs to the cluster
before realizing the cluster object. Regrettably QOM provides no
way to prevent adding children to a realized object and no way for
the parent to be notified when a new child is added to it, so
we don't have any way to enforce/assert this constraint; all
we can do is document it in a comment. We can at least put in a
check that the cluster contains at least one CPU, which should
catch the typical cases of "realized cluster too early" or
"forgot to parent the CPUs into it".

The restriction on how many clusters can exist in the system
is imposed by TCG code which will be added in a subsequent commit,
but the check to enforce it in cluster.c fits better in this one.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20190121152218.9592-3-peter.maydell@linaro.org

hw/cpu/cluster.c

@@ -20,19 +20,65 @@
 
 #include "qemu/osdep.h"
 #include "hw/cpu/cluster.h"
+#include "qom/cpu.h"
 #include "qapi/error.h"
 #include "qemu/module.h"
+#include "qemu/cutils.h"
 
 static Property cpu_cluster_properties[] = {
     DEFINE_PROP_UINT32("cluster-id", CPUClusterState, cluster_id, 0),
     DEFINE_PROP_END_OF_LIST()
 };
 
+typedef struct CallbackData {
+    CPUClusterState *cluster;
+    int cpu_count;
+} CallbackData;
+
+static int add_cpu_to_cluster(Object *obj, void *opaque)
+{
+    CallbackData *cbdata = opaque;
+    CPUState *cpu = (CPUState *)object_dynamic_cast(obj, TYPE_CPU);
+
+    if (cpu) {
+        cpu->cluster_index = cbdata->cluster->cluster_id;
+        cbdata->cpu_count++;
+    }
+    return 0;
+}
+
+static void cpu_cluster_realize(DeviceState *dev, Error **errp)
+{
+    /* Iterate through all our CPU children and set their cluster_index */
+    CPUClusterState *cluster = CPU_CLUSTER(dev);
+    Object *cluster_obj = OBJECT(dev);
+    CallbackData cbdata = {
+        .cluster = cluster,
+        .cpu_count = 0,
+    };
+
+    if (cluster->cluster_id >= MAX_CLUSTERS) {
+        error_setg(errp, "cluster-id must be less than %d", MAX_CLUSTERS);
+        return;
+    }
+
+    object_child_foreach_recursive(cluster_obj, add_cpu_to_cluster, &cbdata);
+
+    /*
+     * A cluster with no CPUs is a bug in the board/SoC code that created it;
+     * if you hit this during development of new code, check that you have
+     * created the CPUs and parented them into the cluster object before
+     * realizing the cluster object.
+     */
+    assert(cbdata.cpu_count > 0);
+}
+
 static void cpu_cluster_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->props = cpu_cluster_properties;
+    dc->realize = cpu_cluster_realize;
 }
 
 static const TypeInfo cpu_cluster_type_info = {

include/hw/cpu/cluster.h

@@ -34,12 +34,36 @@
  * Arm big.LITTLE system) they should be in different clusters. If the CPUs do
  * not have the same view of memory (for example the main CPU and a management
  * controller processor) they should be in different clusters.
+ *
+ * A cluster is created by creating an object of TYPE_CPU_CLUSTER, and then
+ * adding the CPUs to it as QOM child objects (e.g. using the
+ * object_initialize_child() or object_property_add_child() functions).
+ * The CPUs may be either direct children of the cluster object, or indirect
+ * children (e.g. children of children of the cluster object).
+ *
+ * All CPUs must be added as children before the cluster is realized.
+ * (Regrettably QOM provides no way to prevent adding children to a realized
+ * object and no way for the parent to be notified when a new child is added
+ * to it, so this restriction is not checked for, but the system will not
+ * behave correctly if it is not adhered to. The cluster will assert that
+ * it contains at least one CPU, which should catch most inadvertent
+ * violations of this constraint.)
+ *
+ * A CPU which is not put into any cluster will be considered implicitly
+ * to be in a cluster with all the other "loose" CPUs, so all CPUs that are
+ * not assigned to clusters must be identical.
  */
 
 #define TYPE_CPU_CLUSTER "cpu-cluster"
 #define CPU_CLUSTER(obj) \
     OBJECT_CHECK(CPUClusterState, (obj), TYPE_CPU_CLUSTER)
 
+/*
+ * This limit is imposed by TCG, which puts the cluster ID into an
+ * 8 bit field (and uses all-1s for the default "not in any cluster").
+ */
+#define MAX_CLUSTERS 255
+
 /**
  * CPUClusterState:
  * @cluster_id: The cluster ID. This value is for internal use only and should

include/qom/cpu.h

@@ -280,6 +280,11 @@ struct qemu_work_item;
 /**
  * CPUState:
  * @cpu_index: CPU index (informative).
+ * @cluster_index: Identifies which cluster this CPU is in.
+ *   For boards which don't define clusters or for "loose" CPUs not assigned
+ *   to a cluster this will be UNASSIGNED_CLUSTER_INDEX; otherwise it will
+ *   be the same as the cluster-id property of the CPU object's TYPE_CPU_CLUSTER
+ *   QOM parent.
  * @nr_cores: Number of cores within this CPU package.
  * @nr_threads: Number of threads within this CPU.
  * @running: #true if CPU is currently running (lockless).
@@ -405,6 +410,7 @@ struct CPUState {
 
     /* TODO Move common fields from CPUArchState here. */
     int cpu_index;
+    int cluster_index;
     uint32_t halted;
     uint32_t can_do_io;
     int32_t exception_index;
@@ -1111,5 +1117,6 @@ extern const struct VMStateDescription vmstate_cpu_common;
 #endif /* NEED_CPU_H */
 
 #define UNASSIGNED_CPU_INDEX -1
+#define UNASSIGNED_CLUSTER_INDEX -1
 
 #endif

qom/cpu.c

@@ -364,6 +364,7 @@ static void cpu_common_initfn(Object *obj)
     CPUClass *cc = CPU_GET_CLASS(obj);
 
     cpu->cpu_index = UNASSIGNED_CPU_INDEX;
+    cpu->cluster_index = UNASSIGNED_CLUSTER_INDEX;
     cpu->gdb_num_regs = cpu->gdb_num_g_regs = cc->gdb_num_core_regs;
     /* *-user doesn't have configurable SMP topology */
     /* the default value is changed by qemu_init_vcpu() for softmmu */