Commit d41f3e75 authored by Igor Mammedov's avatar Igor Mammedov Committed by Eduardo Habkost
Browse files

numa: make sure that all cpus have has_node_id set if numa is enabled 



It fixes/add missing _PXM object for non mapped CPU (x86)
and missing fdt node (virt-arm).

It ensures that possible_cpus contains complete mapping if
numa is enabled by the time machine_init() is executed.

As result non completely mapped CPUs:
 1) appear in ACPI/fdt blobs
 2) QMP query-hotpluggable-cpus command shows bound nodes for such CPUs
 3) allows to drop checks for has_node_id in numa only code,
   reducing number of invariants incomplete mapping could produce
 4) moves fixup/implicit node init from runtime numa_cpu_pre_plug()
   (when CPU object is created) to machine_numa_finish_init() which
   helps to fix [1, 2] and make possible_cpus complete source
   of numa mapping available even before CPUs are created.

Signed-off-by: default avatarIgor Mammedov <imammedo@redhat.com>
Message-Id: <1496161442-96665-4-git-send-email-imammedo@redhat.com>
Signed-off-by: default avatarEduardo Habkost <ehabkost@redhat.com>
parent 60bed6a3

hw/arm/virt-acpi-build.c

+1 −3
Original line number Diff line number Diff line
@@ -496,12 +496,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) 
    srat->reserved1 = cpu_to_le32(1);



    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(node_id);

        core->proximity = cpu_to_le32(cpu_list->cpus[i].props.node_id);

        core->acpi_processor_uid = cpu_to_le32(i);

        core->flags = cpu_to_le32(1);

    }

hw/core/machine.c

+10 −6
Original line number Diff line number Diff line
@@ -721,19 +721,23 @@ static void machine_numa_finish_init(MachineState *machine) 
        const CPUArchId *cpu_slot = &possible_cpus->cpus[i];



        if (!cpu_slot->props.has_node_id) {

            if (default_mapping) {

            /* fetch default mapping from board and enable it */

            CpuInstanceProperties props = cpu_slot->props;

                props.has_node_id = true;

                machine_set_cpu_numa_node(machine, &props, &error_fatal);

            } else {



            if (!default_mapping) {

                /* record slots with not set mapping,

                 * TODO: make it hard error in future */

                char *cpu_str = cpu_slot_to_string(cpu_slot);

                g_string_append_printf(s, "%sCPU %d [%s]",

                                       s->len ? ", " : "", i, cpu_str);

                g_free(cpu_str);



                /* non mapped cpus used to fallback to node 0 */

                props.node_id = 0;

            }



            props.has_node_id = true;

            machine_set_cpu_numa_node(machine, &props, &error_fatal);

        }

    }

    if (s->len && !qtest_enabled()) {

hw/i386/acpi-build.c

+1 −2
Original line number Diff line number Diff line
@@ -2335,8 +2335,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) 
    srat->reserved1 = cpu_to_le32(1);



    for (i = 0; i < apic_ids->len; i++) {

        int node_id = apic_ids->cpus[i].props.has_node_id ?

            apic_ids->cpus[i].props.node_id : 0;

        int node_id = apic_ids->cpus[i].props.node_id;

        uint32_t apic_id = apic_ids->cpus[i].arch_id;



        if (apic_id < 255) {

hw/i386/pc.c

+1 −3
Original line number Diff line number Diff line
@@ -788,10 +788,8 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms) 
    for (i = 0; i < cpus->len; i++) {

        unsigned int apic_id = cpus->cpus[i].arch_id;

        assert(apic_id < pcms->apic_id_limit);

        if (cpus->cpus[i].props.has_node_id) {

        numa_fw_cfg[apic_id + 1] = cpu_to_le64(cpus->cpus[i].props.node_id);

    }

    }

    for (i = 0; i < nb_numa_nodes; i++) {

        numa_fw_cfg[pcms->apic_id_limit + 1 + i] =

            cpu_to_le64(numa_info[i].node_mem);

numa.c

+5 −11
Original line number Diff line number Diff line
@@ -509,22 +509,16 @@ void parse_numa_opts(MachineState *ms) 


void numa_cpu_pre_plug(const CPUArchId *slot, DeviceState *dev, Error **errp)

{

    int mapped_node_id; /* set by -numa option */

    int node_id = object_property_get_int(OBJECT(dev), "node-id", &error_abort);



    /* by default CPUState::numa_node was 0 if it wasn't set explicitly

     * TODO: make it error when incomplete numa mapping support is removed

     */

    mapped_node_id = slot->props.node_id;

    if (!slot->props.has_node_id) {

        mapped_node_id = 0;

    }



    if (node_id == CPU_UNSET_NUMA_NODE_ID) {

        /* due to bug in libvirt, it doesn't pass node-id from props on

         * device_add as expected, so we have to fix it up here */

        object_property_set_int(OBJECT(dev), mapped_node_id, "node-id", errp);

    } else if (node_id != mapped_node_id) {

        if (slot->props.has_node_id) {

            object_property_set_int(OBJECT(dev), slot->props.node_id,

                                    "node-id", errp);

        }

    } else if (node_id != slot->props.node_id) {

        error_setg(errp, "node-id=%d must match numa node specified "

                   "with -numa option", node_id);

    }