Merge remote-tracking branch 'ehabkost/tags/x86-and-machine-pull-requ…

…est' into staging

x86 and machine queue, 2017-05-11

Highlights:
* New "-numa cpu" option
* NUMA distance configuration
* migration/i386 vmstatification

# gpg: Signature made Thu 11 May 2017 08:16:07 PM BST
# gpg:                using RSA key 0x2807936F984DC5A6
# gpg: Good signature from "Eduardo Habkost <ehabkost@redhat.com>"
# gpg: Note: This key has expired!
# Primary key fingerprint: 5A32 2FD5 ABC4 D3DB ACCF  D1AA 2807 936F 984D C5A6

* ehabkost/tags/x86-and-machine-pull-request: (29 commits)
  migration/i386: Remove support for pre-0.12 formats
  vmstatification: i386 FPReg
  migration/i386: Remove old non-softfloat 64bit FP support
  tests: check -numa node,cpu=props_list usecase
  numa: add '-numa cpu,...' option for property based node mapping
  numa: remove node_cpu bitmaps as they are no longer used
  numa: use possible_cpus for not mapped CPUs check
  machine: call machine init from wrapper
  numa: remove no longer need numa_post_machine_init()
  tests: numa: add case for QMP command query-cpus
  QMP: include CpuInstanceProperties into query_cpus output output
  virt-arm: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu()
  spapr: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu()
  pc: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu()
  numa: do default mapping based on possible_cpus instead of node_cpu bitmaps
  numa: mirror cpu to node mapping in MachineState::possible_cpus
  numa: add check that board supports cpu_index to node mapping
  virt-arm: add node-id property to CPU
  pc: add node-id property to CPU
  spapr: add node-id property to sPAPR core
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

cpus.c

@@ -50,6 +50,7 @@
 #include "qapi-event.h"
 #include "hw/nmi.h"
 #include "sysemu/replay.h"
+#include "hw/boards.h"
 
 #ifdef CONFIG_LINUX
 
@@ -1865,6 +1866,8 @@ void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
 
 CpuInfoList *qmp_query_cpus(Error **errp)
 {
+    MachineState *ms = MACHINE(qdev_get_machine());
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
     CpuInfoList *head = NULL, *cur_item = NULL;
     CPUState *cpu;
 
@@ -1915,6 +1918,13 @@ CpuInfoList *qmp_query_cpus(Error **errp)
 #else
         info->value->arch = CPU_INFO_ARCH_OTHER;
 #endif
+        info->value->has_props = !!mc->cpu_index_to_instance_props;
+        if (info->value->has_props) {
+            CpuInstanceProperties *props;
+            props = g_malloc0(sizeof(*props));
+            *props = mc->cpu_index_to_instance_props(ms, cpu->cpu_index);
+            info->value->props = props;
+        }
 
         /* XXX: waiting for the qapi to support GSList */
         if (!cur_item) {

hw/acpi/aml-build.c

@@ -24,6 +24,7 @@
 #include "hw/acpi/aml-build.h"
 #include "qemu/bswap.h"
 #include "qemu/bitops.h"
+#include "sysemu/numa.h"
 
 static GArray *build_alloc_array(void)
 {
@@ -1609,3 +1610,28 @@ void build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base,
     numamem->base_addr = cpu_to_le64(base);
     numamem->range_length = cpu_to_le64(len);
 }
+
+/*
+ * ACPI spec 5.2.17 System Locality Distance Information Table
+ * (Revision 2.0 or later)
+ */
+void build_slit(GArray *table_data, BIOSLinker *linker)
+{
+    int slit_start, i, j;
+    slit_start = table_data->len;
+
+    acpi_data_push(table_data, sizeof(AcpiTableHeader));
+
+    build_append_int_noprefix(table_data, nb_numa_nodes, 8);
+    for (i = 0; i < nb_numa_nodes; i++) {
+        for (j = 0; j < nb_numa_nodes; j++) {
+            assert(numa_info[i].distance[j]);
+            build_append_int_noprefix(table_data, numa_info[i].distance[j], 1);
+        }
+    }
+
+    build_header(linker, table_data,
+                 (void *)(table_data->data + slit_start),
+                 "SLIT",
+                 table_data->len - slit_start, 1, NULL, NULL);
+}

hw/acpi/cpu.c

@@ -503,7 +503,6 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
 
         /* build Processor object for each processor */
         for (i = 0; i < arch_ids->len; i++) {
-            int j;
             Aml *dev;
             Aml *uid = aml_int(i);
             GArray *madt_buf = g_array_new(0, 1, 1);
@@ -557,9 +556,9 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
              * as a result _PXM is required for all CPUs which might
              * be hot-plugged. For simplicity, add it for all CPUs.
              */
-            j = numa_get_node_for_cpu(i);
-            if (j < nb_numa_nodes) {
-                aml_append(dev, aml_name_decl("_PXM", aml_int(j)));
+            if (arch_ids->cpus[i].props.has_node_id) {
+                aml_append(dev, aml_name_decl("_PXM",
+                           aml_int(arch_ids->cpus[i].props.node_id)));
             }
 
             aml_append(cpus_dev, dev);

hw/arm/virt-acpi-build.c

@@ -486,30 +486,25 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     AcpiSystemResourceAffinityTable *srat;
     AcpiSratProcessorGiccAffinity *core;
     AcpiSratMemoryAffinity *numamem;
-    int i, j, srat_start;
+    int i, srat_start;
     uint64_t mem_base;
-    uint32_t *cpu_node = g_malloc0(vms->smp_cpus * sizeof(uint32_t));
-
-    for (i = 0; i < vms->smp_cpus; i++) {
-        j = numa_get_node_for_cpu(i);
-        if (j < nb_numa_nodes) {
-                cpu_node[i] = j;
-        }
-    }
+    MachineClass *mc = MACHINE_GET_CLASS(vms);
+    const CPUArchIdList *cpu_list = mc->possible_cpu_arch_ids(MACHINE(vms));
 
     srat_start = table_data->len;
     srat = acpi_data_push(table_data, sizeof(*srat));
     srat->reserved1 = cpu_to_le32(1);
 
-    for (i = 0; i < vms->smp_cpus; ++i) {
+    for (i = 0; i < cpu_list->len; ++i) {
+        int node_id = cpu_list->cpus[i].props.has_node_id ?
+            cpu_list->cpus[i].props.node_id : 0;
         core = acpi_data_push(table_data, sizeof(*core));
         core->type = ACPI_SRAT_PROCESSOR_GICC;
         core->length = sizeof(*core);
-        core->proximity = cpu_to_le32(cpu_node[i]);
+        core->proximity = cpu_to_le32(node_id);
         core->acpi_processor_uid = cpu_to_le32(i);
         core->flags = cpu_to_le32(1);
     }
-    g_free(cpu_node);
 
     mem_base = vms->memmap[VIRT_MEM].base;
     for (i = 0; i < nb_numa_nodes; ++i) {

hw/arm/virt.c

@@ -338,7 +338,7 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms)
 {
     int cpu;
     int addr_cells = 1;
-    unsigned int i;
+    const MachineState *ms = MACHINE(vms);
 
     /*
      * From Documentation/devicetree/bindings/arm/cpus.txt
@@ -369,6 +369,7 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms)
     for (cpu = vms->smp_cpus - 1; cpu >= 0; cpu--) {
         char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu);
         ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu));
+        CPUState *cs = CPU(armcpu);
 
         qemu_fdt_add_subnode(vms->fdt, nodename);
         qemu_fdt_setprop_string(vms->fdt, nodename, "device_type", "cpu");
@@ -389,9 +390,9 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms)
                                   armcpu->mp_affinity);
         }
 
-        i = numa_get_node_for_cpu(cpu);
-        if (i < nb_numa_nodes) {
-            qemu_fdt_setprop_cell(vms->fdt, nodename, "numa-node-id", i);
+        if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) {
+            qemu_fdt_setprop_cell(vms->fdt, nodename, "numa-node-id",
+                ms->possible_cpus->cpus[cs->cpu_index].props.node_id);
         }
 
         g_free(nodename);
@@ -1194,10 +1195,35 @@ void virt_machine_done(Notifier *notifier, void *data)
     virt_build_smbios(vms);
 }
 
+static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
+{
+    uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER;
+    VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
+
+    if (!vmc->disallow_affinity_adjustment) {
+        /* Adjust MPIDR like 64-bit KVM hosts, which incorporate the
+         * GIC's target-list limitations. 32-bit KVM hosts currently
+         * always create clusters of 4 CPUs, but that is expected to
+         * change when they gain support for gicv3. When KVM is enabled
+         * it will override the changes we make here, therefore our
+         * purposes are to make TCG consistent (with 64-bit KVM hosts)
+         * and to improve SGI efficiency.
+         */
+        if (vms->gic_version == 3) {
+            clustersz = GICV3_TARGETLIST_BITS;
+        } else {
+            clustersz = GIC_TARGETLIST_BITS;
+        }
+    }
+    return arm_cpu_mp_affinity(idx, clustersz);
+}
+
 static void machvirt_init(MachineState *machine)
 {
     VirtMachineState *vms = VIRT_MACHINE(machine);
     VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(machine);
+    MachineClass *mc = MACHINE_GET_CLASS(machine);
+    const CPUArchIdList *possible_cpus;
     qemu_irq pic[NUM_IRQS];
     MemoryRegion *sysmem = get_system_memory();
     MemoryRegion *secure_sysmem = NULL;
@@ -1210,7 +1236,6 @@ static void machvirt_init(MachineState *machine)
     CPUClass *cc;
     Error *err = NULL;
     bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
-    uint8_t clustersz;
 
     if (!cpu_model) {
         cpu_model = "cortex-a15";
@@ -1263,10 +1288,8 @@ static void machvirt_init(MachineState *machine)
      */
     if (vms->gic_version == 3) {
         virt_max_cpus = vms->memmap[VIRT_GIC_REDIST].size / 0x20000;
-        clustersz = GICV3_TARGETLIST_BITS;
     } else {
         virt_max_cpus = GIC_NCPU;
-        clustersz = GIC_TARGETLIST_BITS;
     }
 
     if (max_cpus > virt_max_cpus) {
@@ -1324,21 +1347,35 @@ static void machvirt_init(MachineState *machine)
         exit(1);
     }
 
-    for (n = 0; n < smp_cpus; n++) {
-        Object *cpuobj = object_new(typename);
-        if (!vmc->disallow_affinity_adjustment) {
-            /* Adjust MPIDR like 64-bit KVM hosts, which incorporate the
-             * GIC's target-list limitations. 32-bit KVM hosts currently
-             * always create clusters of 4 CPUs, but that is expected to
-             * change when they gain support for gicv3. When KVM is enabled
-             * it will override the changes we make here, therefore our
-             * purposes are to make TCG consistent (with 64-bit KVM hosts)
-             * and to improve SGI efficiency.
-             */
-            uint8_t aff1 = n / clustersz;
-            uint8_t aff0 = n % clustersz;
-            object_property_set_int(cpuobj, (aff1 << ARM_AFF1_SHIFT) | aff0,
-                                    "mp-affinity", NULL);
+    possible_cpus = mc->possible_cpu_arch_ids(machine);
+    for (n = 0; n < possible_cpus->len; n++) {
+        Object *cpuobj;
+        CPUState *cs;
+        int node_id;
+
+        if (n >= smp_cpus) {
+            break;
+        }
+
+        cpuobj = object_new(typename);
+        object_property_set_int(cpuobj, possible_cpus->cpus[n].arch_id,
+                                "mp-affinity", NULL);
+
+        cs = CPU(cpuobj);
+        cs->cpu_index = n;
+
+        node_id = possible_cpus->cpus[cs->cpu_index].props.node_id;
+        if (!possible_cpus->cpus[cs->cpu_index].props.has_node_id) {
+            /* by default CPUState::numa_node was 0 if it's not set via CLI
+             * keep it this way for now but in future we probably should
+             * refuse to start up with incomplete numa mapping */
+             node_id = 0;
+        }
+        if (cs->numa_node == CPU_UNSET_NUMA_NODE_ID) {
+            cs->numa_node = node_id;
+        } else {
+            /* CPU isn't device_add compatible yet, this shouldn't happen */
+            error_setg(&error_abort, "user set node-id not implemented");
         }
 
         if (!vms->secure) {
@@ -1518,6 +1555,46 @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp)
     }
 }
 
+static CpuInstanceProperties
+virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
+{
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms);
+
+    assert(cpu_index < possible_cpus->len);
+    return possible_cpus->cpus[cpu_index].props;
+}
+
+static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
+{
+    int n;
+    VirtMachineState *vms = VIRT_MACHINE(ms);
+
+    if (ms->possible_cpus) {
+        assert(ms->possible_cpus->len == max_cpus);
+        return ms->possible_cpus;
+    }
+
+    ms->possible_cpus = g_malloc0(sizeof(CPUArchIdList) +
+                                  sizeof(CPUArchId) * max_cpus);
+    ms->possible_cpus->len = max_cpus;
+    for (n = 0; n < ms->possible_cpus->len; n++) {
+        ms->possible_cpus->cpus[n].arch_id =
+            virt_cpu_mp_affinity(vms, n);
+        ms->possible_cpus->cpus[n].props.has_thread_id = true;
+        ms->possible_cpus->cpus[n].props.thread_id = n;
+
+        /* default distribution of CPUs over NUMA nodes */
+        if (nb_numa_nodes) {
+            /* preset values but do not enable them i.e. 'has_node_id = false',
+             * numa init code will enable them later if manual mapping wasn't
+             * present on CLI */
+            ms->possible_cpus->cpus[n].props.node_id = n % nb_numa_nodes;
+        }
+    }
+    return ms->possible_cpus;
+}
+
 static void virt_machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
@@ -1534,6 +1611,8 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     mc->pci_allow_0_address = true;
     /* We know we will never create a pre-ARMv7 CPU which needs 1K pages */
     mc->minimum_page_bits = 12;
+    mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids;
+    mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
 }
 
 static const TypeInfo virt_machine_info = {