Re: [Qemu-devel] [RFC PATCH v2 7/9] spapr: CPU hotplug support

[Igor Mammedov <imammedo@redhat.com>]

On Wed, 16 Mar 2016 16:19:33 +1100
David Gibson <david@gibson.dropbear.id.au> wrote:

> On Fri, Mar 11, 2016 at 10:24:36AM +0530, Bharata B Rao wrote:
> > Set up device tree entries for the hotplugged CPU core and use the
> > exising RTAS event logging infrastructure to send CPU hotplug notification
> > to the guest.
> > 
> > Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
> > ---
> >  hw/ppc/spapr.c                  | 64 ++++++++++++++++++++++++++++++++++++++
> >  hw/ppc/spapr_cpu_core.c         | 69 +++++++++++++++++++++++++++++++++++++++++
> >  hw/ppc/spapr_events.c           |  3 ++
> >  hw/ppc/spapr_rtas.c             | 24 ++++++++++++++
> >  include/hw/ppc/spapr.h          |  2 ++
> >  include/hw/ppc/spapr_cpu_core.h |  2 ++
> >  6 files changed, 164 insertions(+)
> > 
> > diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> > index cffe8c8..822c87d 100644
> > --- a/hw/ppc/spapr.c
> > +++ b/hw/ppc/spapr.c
> > @@ -603,6 +603,18 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
> >      size_t page_sizes_prop_size;
> >      uint32_t vcpus_per_socket = smp_threads * smp_cores;
> >      uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
> > +    sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(qdev_get_machine());
> > +    sPAPRDRConnector *drc;
> > +    sPAPRDRConnectorClass *drck;
> > +    int drc_index;
> > +
> > +    if (smc->dr_cpu_enabled) {
> > +        drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index);
> > +        g_assert(drc);  
> 
> Small nit: rather than asserting here it might be simpler to just
> check for drc != NULL instead of checking smc->dr_cpu_enabled.  That
> should have the same effect for now, and will be correct if we ever
> have some pluggable and some non-pluggable CPUs...
> 
> > +        drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
> > +        drc_index = drck->get_index(drc);
> > +        _FDT((fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index)));
> > +    }
> >  
> >      /* Note: we keep CI large pages off for now because a 64K capable guest
> >       * provisioned with large pages might otherwise try to map a qemu
> > @@ -987,6 +999,16 @@ static void spapr_finalize_fdt(sPAPRMachineState *spapr,
> >          _FDT(spapr_drc_populate_dt(fdt, 0, NULL, SPAPR_DR_CONNECTOR_TYPE_LMB));
> >      }
> >  
> > +    if (smc->dr_cpu_enabled) {
> > +        int offset = fdt_path_offset(fdt, "/cpus");
> > +        ret = spapr_drc_populate_dt(fdt, offset, NULL,
> > +                                    SPAPR_DR_CONNECTOR_TYPE_CPU);
> > +        if (ret < 0) {
> > +            error_report("Couldn't set up CPU DR device tree properties");
> > +            exit(1);
> > +        }
> > +    }
> > +
> >      _FDT((fdt_pack(fdt)));
> >  
> >      if (fdt_totalsize(fdt) > FDT_MAX_SIZE) {
> > @@ -1622,6 +1644,8 @@ static void spapr_boot_set(void *opaque, const char *boot_device,
> >  void spapr_cpu_init(sPAPRMachineState *spapr, PowerPCCPU *cpu, Error **errp)
> >  {
> >      CPUPPCState *env = &cpu->env;
> > +    CPUState *cs = CPU(cpu);
> > +    int i;
> >  
> >      /* Set time-base frequency to 512 MHz */
> >      cpu_ppc_tb_init(env, TIMEBASE_FREQ);
> > @@ -1646,6 +1670,14 @@ void spapr_cpu_init(sPAPRMachineState *spapr, PowerPCCPU *cpu, Error **errp)
> >          }
> >      }
> >  
> > +    /* Set NUMA node for the added CPUs  */
> > +    for (i = 0; i < nb_numa_nodes; i++) {
> > +        if (test_bit(cs->cpu_index, numa_info[i].node_cpu)) {
> > +            cs->numa_node = i;
> > +            break;
> > +        }
> > +    }
> > +
> >      xics_cpu_setup(spapr->icp, cpu);
> >  
> >      qemu_register_reset(spapr_cpu_reset, cpu);
> > @@ -1824,6 +1856,11 @@ static void ppc_spapr_init(MachineState *machine)
> >  
> >          for (i = 0; i < spapr_max_cores; i++) {
> >              int core_dt_id = i * smt;
> > +            sPAPRDRConnector *drc =
> > +                spapr_dr_connector_new(OBJECT(spapr),
> > +                                       SPAPR_DR_CONNECTOR_TYPE_CPU, core_dt_id);
> > +
> > +            qemu_register_reset(spapr_drc_reset, drc);  
> 
> ...at least it will be if you make construction of the DRC object
> conditional on dr_cpu_enabled.
> 
> >              if (i < spapr_cores) {
> >                  Object *core  = object_new(TYPE_SPAPR_CPU_CORE);
> > @@ -2246,6 +2283,27 @@ out:
> >      error_propagate(errp, local_err);
> >  }
> >  
> > +void *spapr_populate_hotplug_cpu_dt(DeviceState *dev, CPUState *cs,
> > +                                    int *fdt_offset, sPAPRMachineState *spapr)
> > +{
> > +    PowerPCCPU *cpu = POWERPC_CPU(cs);
> > +    DeviceClass *dc = DEVICE_GET_CLASS(cs);
> > +    int id = ppc_get_vcpu_dt_id(cpu);
> > +    void *fdt;
> > +    int offset, fdt_size;
> > +    char *nodename;
> > +
> > +    fdt = create_device_tree(&fdt_size);
> > +    nodename = g_strdup_printf("%s@%x", dc->fw_name, id);
> > +    offset = fdt_add_subnode(fdt, 0, nodename);
> > +
> > +    spapr_populate_cpu_dt(cs, fdt, offset, spapr);
> > +    g_free(nodename);
> > +
> > +    *fdt_offset = offset;
> > +    return fdt;
> > +}
> > +
> >  static void spapr_machine_device_plug(HotplugHandler *hotplug_dev,
> >                                        DeviceState *dev, Error **errp)
> >  {
> > @@ -2286,6 +2344,12 @@ static void spapr_machine_device_plug(HotplugHandler *hotplug_dev,
> >          }
> >  
> >          spapr_memory_plug(hotplug_dev, dev, node, errp);
> > +    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
> > +        if (!smc->dr_cpu_enabled && dev->hotplugged) {
> > +            error_setg(errp, "CPU hotplug not supported for this machine");
> > +            return;
> > +        }
> > +        spapr_core_plug(hotplug_dev, dev, errp);
> >      }
> >  }
> >  
> > diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
> > index 8c6d71d..db8de32 100644
> > --- a/hw/ppc/spapr_cpu_core.c
> > +++ b/hw/ppc/spapr_cpu_core.c
> > @@ -15,6 +15,75 @@
> >  #include <sysemu/cpus.h>
> >  #include "target-ppc/kvm_ppc.h"
> >  
> > +void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
> > +                     Error **errp)
> > +{
> > +    sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(qdev_get_machine());
> > +    sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
> > +    sPAPRCPUCore *core = SPAPR_CPU_CORE(OBJECT(dev));
> > +    CPUState *cs = CPU(&core->threads[0]);
> > +    sPAPRDRConnector *drc;
> > +    sPAPRDRConnectorClass *drck;
> > +    Error *local_err = NULL;
> > +    void *fdt = NULL;
> > +    int fdt_offset = 0;
> > +    int core_id, core_dt_id;
> > +    int smt = kvmppc_smt_threads();
> > +
> > +    /* TODO: Should we cache core_id in sPAPRCPUCore ? */
> > +    core_dt_id = object_property_get_int(OBJECT(dev), "core",
> > &local_err);  
> 
> As Igor pointed out elsewhere you should just be able to do
> CPU_CORE(dev)->core.
not exactly like this, from what I know that's not approved style,
it should be something like this:

CPUCore *cc = CPU_CORE(dev);

  ... cc->core ...

> 
> > +    if (local_err) {
> > +        error_propagate(errp, local_err);
> > +        return;
> > +    }
> > +    drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, core_dt_id);
> > +    core_id = core_dt_id / smt;
> > +    spapr->cores[core_id] = OBJECT(dev);
> > +
> > +    if (!smc->dr_cpu_enabled) {
> > +        /*
> > +         * This is a cold plugged CPU core but the machine doesn't support
> > +         * DR. So skip the hotplug path ensuring that the core is brought
> > +         * up online with out an associated DR connector.
> > +         */
> > +        return;
> > +    }
> > +
> > +    g_assert(drc);
> > +
> > +    /*
> > +     * Setup CPU DT entries only for hotplugged CPUs. For boot time or
> > +     * coldplugged CPUs DT entries are setup in spapr_finalize_fdt().
> > +     */
> > +    if (dev->hotplugged) {
> > +        fdt = spapr_populate_hotplug_cpu_dt(dev, cs, &fdt_offset, spapr);
> > +        dev->hotplugged = true;
> > +    }
> > +
> > +    drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
> > +    drck->attach(drc, dev, fdt, fdt_offset, !dev->hotplugged, &local_err);
> > +    if (local_err) {
> > +        g_free(fdt);
> > +        spapr->cores[core_id] = NULL;
> > +        error_propagate(errp, local_err);
> > +        return;
> > +    }
> > +
> > +    if (dev->hotplugged) {
> > +        /*
> > +         * Send hotplug notification interrupt to the guest only in case
> > +         * of hotplugged CPUs.
> > +         */
> > +        spapr_hotplug_req_add_by_index(drc);
> > +    } else {
> > +        /*
> > +         * Set the right DRC states for cold plugged CPU.
> > +         */
> > +        drck->set_allocation_state(drc, SPAPR_DR_ALLOCATION_STATE_USABLE);
> > +        drck->set_isolation_state(drc, SPAPR_DR_ISOLATION_STATE_UNISOLATED);
> > +    }
> > +}
> > +
> >  static void spapr_cpu_core_create_threads(sPAPRCPUCore *core, int threads,
> >                                            Error **errp)
> >  {
> > diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
> > index 39f4682..10340e1 100644
> > --- a/hw/ppc/spapr_events.c
> > +++ b/hw/ppc/spapr_events.c
> > @@ -437,6 +437,9 @@ static void spapr_hotplug_req_event(uint8_t hp_id, uint8_t hp_action,
> >      case SPAPR_DR_CONNECTOR_TYPE_LMB:
> >          hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_MEMORY;
> >          break;
> > +    case SPAPR_DR_CONNECTOR_TYPE_CPU:
> > +        hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_CPU;
> > +        break;
> >      default:
> >          /* we shouldn't be signaling hotplug events for resources
> >           * that don't support them
> > diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
> > index b7c5ebd..cc0369e 100644
> > --- a/hw/ppc/spapr_rtas.c
> > +++ b/hw/ppc/spapr_rtas.c
> > @@ -34,6 +34,7 @@
> >  
> >  #include "hw/ppc/spapr.h"
> >  #include "hw/ppc/spapr_vio.h"
> > +#include "hw/ppc/ppc.h"
> >  #include "qapi-event.h"
> >  #include "hw/boards.h"
> >  
> > @@ -161,6 +162,27 @@ static void rtas_query_cpu_stopped_state(PowerPCCPU *cpu_,
> >      rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
> >  }
> >  
> > +/*
> > + * Set the timebase offset of the CPU to that of first CPU.
> > + * This helps hotplugged CPU to have the correct timebase offset.
> > + */
> > +static void spapr_cpu_update_tb_offset(PowerPCCPU *cpu)
> > +{
> > +    PowerPCCPU *fcpu = POWERPC_CPU(first_cpu);
> > +
> > +    cpu->env.tb_env->tb_offset = fcpu->env.tb_env->tb_offset;
> > +}
> > +
> > +static void spapr_cpu_set_endianness(PowerPCCPU *cpu)
> > +{
> > +    PowerPCCPU *fcpu = POWERPC_CPU(first_cpu);
> > +    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(fcpu);
> > +
> > +    if (!pcc->interrupts_big_endian(fcpu)) {
> > +        cpu->env.spr[SPR_LPCR] |= LPCR_ILE;
> > +    }
> > +}
> > +
> >  static void rtas_start_cpu(PowerPCCPU *cpu_, sPAPRMachineState *spapr,
> >                             uint32_t token, uint32_t nargs,
> >                             target_ulong args,
> > @@ -197,6 +219,8 @@ static void rtas_start_cpu(PowerPCCPU *cpu_, sPAPRMachineState *spapr,
> >          env->nip = start;
> >          env->gpr[3] = r3;
> >          cs->halted = 0;
> > +        spapr_cpu_set_endianness(cpu);
> > +        spapr_cpu_update_tb_offset(cpu);
> >  
> >          qemu_cpu_kick(cs);
> >  
> > diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
> > index c099c3c..8957072 100644
> > --- a/include/hw/ppc/spapr.h
> > +++ b/include/hw/ppc/spapr.h
> > @@ -589,6 +589,8 @@ void spapr_hotplug_req_remove_by_count(sPAPRDRConnectorType drc_type,
> >                                            uint32_t count);
> >  void spapr_cpu_init(sPAPRMachineState *spapr, PowerPCCPU *cpu, Error **errp);
> >  void spapr_cpu_reset(void *opaque);
> > +void *spapr_populate_hotplug_cpu_dt(DeviceState *dev, CPUState *cs,
> > +                                    int *fdt_offset, sPAPRMachineState *spapr);
> >  
> >  /* rtas-configure-connector state */
> >  struct sPAPRConfigureConnectorState {
> > diff --git a/include/hw/ppc/spapr_cpu_core.h b/include/hw/ppc/spapr_cpu_core.h
> > index 48fb76a..980d8ae 100644
> > --- a/include/hw/ppc/spapr_cpu_core.h
> > +++ b/include/hw/ppc/spapr_cpu_core.h
> > @@ -25,4 +25,6 @@ typedef struct sPAPRCPUCore {
> >      PowerPCCPU *threads;
> >  } sPAPRCPUCore;
> >  
> > +void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
> > +                     Error **errp);
> >  #endif  
>