Re: [Qemu-devel] [PATCH for-2.10 10/23] numa: mirror cpu to node mapping in MachineState::possible_cpus

[Eduardo Habkost]

On Wed, Mar 22, 2017 at 02:32:35PM +0100, Igor Mammedov wrote:
> Introduce machine_set_cpu_numa_node() helper that stores
> node mapping for CPU in MachineState::possible_cpus.
> CPU and node it belongs to is specified by 'props' argument.
> 
> Patch doesn't remove old way of storing mapping in
> numa_info[X].node_cpu as removing it at the same time
> makes patch rather big. Instead it just mirrors mapping
> in possible_cpus and follow up per target patches will
> switch to possible_cpus and numa_info[X].node_cpu will
> be removed once there isn't any users left.
> 
> Signed-off-by: Igor Mammedov <address@hidden>

So, this patch is the one that makes "-numa" and "-numa cpu"
affect query-hotpluggable-cpus output.

Before this patch:

  $ qemu-system-x86_64 -smp 2 -m 2G -numa node -numa node -numa node -numa node
  [run qmp-shell]
  (QEMU) query-hotpluggable-cpus
  {
      "return": [
          {
              "qom-path": "/machine/unattached/device[2]",
              "type": "qemu64-x86_64-cpu",
              "vcpus-count": 1,
              "props": {
                  "socket-id": 1,
                  "core-id": 0,
                  "thread-id": 0
              }
          },
          {
              "qom-path": "/machine/unattached/device[0]",
              "type": "qemu64-x86_64-cpu",
              "vcpus-count": 1,
              "props": {
                  "socket-id": 0,
                  "core-id": 0,
                  "thread-id": 0
              }
          }
      ]
  }


After this patch:

  $ qemu-system-x86_64 -smp 2 -m 2G -numa node -numa node -numa node -numa node
  [run qmp-shell]
  (QEMU) query-hotpluggable-cpus
  {
      "return": [
          {
              "qom-path": "/machine/unattached/device[2]",
              "type": "qemu64-x86_64-cpu",
              "vcpus-count": 1,
              "props": {
                  "socket-id": 1,
                  "node-id": 1,
                  "core-id": 0,
                  "thread-id": 0
              }
          },
          {
              "qom-path": "/machine/unattached/device[0]",
              "type": "qemu64-x86_64-cpu",
              "vcpus-count": 1,
              "props": {
                  "socket-id": 0,
                  "node-id": 0,
                  "core-id": 0,
                  "thread-id": 0
              }
          }
      ]
  }


As noted in another message, I am not sure we really should make
"-numa" affect query-hotpluggable-cpus output unconditionally (I
believe we shouldn't). But we do, we need to document this very
clearly.


> ---
>  include/hw/boards.h |  2 ++
>  hw/core/machine.c   | 68 
> +++++++++++++++++++++++++++++++++++++++++++++++++++++
>  numa.c              |  8 +++++++
>  3 files changed, 78 insertions(+)
> 
> diff --git a/include/hw/boards.h b/include/hw/boards.h
> index 1dd0fde..40f30f1 100644
> --- a/include/hw/boards.h
> +++ b/include/hw/boards.h
> @@ -42,6 +42,8 @@ bool machine_dump_guest_core(MachineState *machine);
>  bool machine_mem_merge(MachineState *machine);
>  void machine_register_compat_props(MachineState *machine);
>  HotpluggableCPUList *machine_query_hotpluggable_cpus(MachineState *machine);
> +void machine_set_cpu_numa_node(MachineState *machine,
> +                               CpuInstanceProperties *props, Error **errp);
>  
>  /**
>   * CPUArchId:
> diff --git a/hw/core/machine.c b/hw/core/machine.c
> index 0d92672..6ff0b45 100644
> --- a/hw/core/machine.c
> +++ b/hw/core/machine.c
> @@ -388,6 +388,74 @@ HotpluggableCPUList 
> *machine_query_hotpluggable_cpus(MachineState *machine)
>      return head;
>  }
>  
> +void machine_set_cpu_numa_node(MachineState *machine,
> +                               CpuInstanceProperties *props, Error **errp)
> +{
> +    MachineClass *mc = MACHINE_GET_CLASS(machine);
> +    bool match = false;
> +    int i;
> +
> +    if (!mc->possible_cpu_arch_ids) {
> +        error_setg(errp, "mapping of CPUs to NUMA node is not supported");
> +        return;
> +    }
> +
> +    /* force board to initialize possible_cpus if it hasn't been done yet */
> +    mc->possible_cpu_arch_ids(machine);
> +
> +    for (i = 0; i < machine->possible_cpus->len; i++) {
> +        CPUArchId *slot = &machine->possible_cpus->cpus[i];
> +
> +        /* reject unsupported by board properties */
> +        if (props->has_thread_id && !slot->props.has_thread_id) {
> +            error_setg(errp, "thread-id is not supported");
> +            return;
> +        }
> +
> +        if (props->has_core_id && !slot->props.has_core_id) {
> +            error_setg(errp, "core-id is not supported");
> +            return;
> +        }
> +
> +        if (props->has_socket_id && !slot->props.has_socket_id) {
> +            error_setg(errp, "socket-id is not supported");
> +            return;
> +        }
> +
> +        /* skip slots with explicit mismatch */
> +        if (props->has_thread_id && props->thread_id != 
> slot->props.thread_id) {
> +                continue;
> +        }
> +
> +        if (props->has_core_id && props->core_id != slot->props.core_id) {
> +                continue;
> +        }
> +
> +        if (props->has_socket_id && props->socket_id != 
> slot->props.socket_id) {
> +                continue;
> +        }
> +
> +        /* reject assignment if slot is already assigned, for compatibility
> +         * of legacy cpu_index mapping with SPAPR core based mapping do not
> +         * error out if cpu thread and matched core have the same node-id */
> +        if (slot->props.has_node_id &&
> +            slot->props.node_id != props->node_id) {
> +            error_setg(errp, "CPU is already assigned to node-id: %" PRId64,
> +                       slot->props.node_id);
> +            return;
> +        }
> +
> +        /* assign slot to node as it's matched '-numa cpu' key */
> +        match = true;
> +        slot->props.node_id = props->node_id;
> +        slot->props.has_node_id = props->has_node_id;
> +    }
> +
> +    if (!match) {
> +        error_setg(errp, "no match found");
> +    }
> +}
> +
>  static void machine_class_init(ObjectClass *oc, void *data)
>  {
>      MachineClass *mc = MACHINE_CLASS(oc);
> diff --git a/numa.c b/numa.c
> index 24c596d..44057f1 100644
> --- a/numa.c
> +++ b/numa.c
> @@ -169,6 +169,7 @@ static void numa_node_parse(MachineState *ms, 
> NumaNodeOptions *node,
>          exit(1);
>      }
>      for (cpus = node->cpus; cpus; cpus = cpus->next) {
> +        CpuInstanceProperties props;
>          if (cpus->value >= max_cpus) {
>              error_setg(errp,
>                         "CPU index (%" PRIu16 ")"
> @@ -177,6 +178,10 @@ static void numa_node_parse(MachineState *ms, 
> NumaNodeOptions *node,
>              return;
>          }
>          bitmap_set(numa_info[nodenr].node_cpu, cpus->value, 1);
> +        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, &error_fatal);
>      }
>  
>      if (node->has_mem && node->has_memdev) {
> @@ -393,9 +398,12 @@ void parse_numa_opts(MachineState *ms)
>          if (i == nb_numa_nodes) {
>              for (i = 0; i < max_cpus; i++) {
>                  CpuInstanceProperties props;
> +                /* fetch default mapping from board and enable it */
>                  props = mc->cpu_index_to_instance_props(ms, i);
> +                props.has_node_id = true;
>  
>                  set_bit(i, numa_info[props.node_id].node_cpu);
> +                machine_set_cpu_numa_node(ms, &props, &error_fatal);
>              }
>          }
>  
> -- 
> 2.7.4
> 
> 

-- 
Eduardo