Re: [qemu-s390x] [PATCH v4 14/15] spapr: add hotplug hooks for PHB hotplug

[David Hildenbrand]

On 12.02.19 19:25, Greg Kurz wrote:
> Hotplugging PHBs is a machine-level operation, but PHBs reside on the
> main system bus, so we register spapr machine as the handler for the
> main system bus.
> 
> Provide the usual pre-plug, plug and unplug-request handlers.
> 
> Move the checking of the PHB index to the pre-plug handler. It is okay
> to do that and assert in the realize function because the pre-plug
> handler is always called, even for the oldest machine types we support.
> 
> Unlike with other device types, there are some cases where we cannot
> provide the FDT fragment of the PHB from the plug handler, eg, before
> KVMPPC_H_UPDATE_DT was called. Do this from a DRC callback that is
> called just before the first FDT fragment is exposed to the guest.
> 
> Signed-off-by: Michael Roth <address@hidden>
> (Fixed interrupt controller phandle in "interrupt-map" and
>  TCE table size in "ibm,dma-window" FDT fragment, Greg Kurz)
> Signed-off-by: Greg Kurz <address@hidden>
> ---
> v4: - populate FDT fragment in a DRC callback
> v3: - reworked phandle handling some more
> v2: - reworked phandle handling
>     - sync LSIs to KVM
> ---
> ---
>  hw/ppc/spapr.c         |  121 
> ++++++++++++++++++++++++++++++++++++++++++++++++
>  hw/ppc/spapr_drc.c     |    2 +
>  hw/ppc/spapr_pci.c     |   16 ------
>  include/hw/ppc/spapr.h |    5 ++
>  4 files changed, 127 insertions(+), 17 deletions(-)
> 
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index 021758825b7e..06ce0babcb54 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -2930,6 +2930,11 @@ static void spapr_machine_init(MachineState *machine)
>      register_savevm_live(NULL, "spapr/htab", -1, 1,
>                           &savevm_htab_handlers, spapr);
>  
> +    if (smc->dr_phb_enabled) {
> +        qbus_set_hotplug_handler(sysbus_get_default(), OBJECT(machine),
> +                                 &error_fatal);
> +    }
> +
>      qemu_register_boot_set(spapr_boot_set, spapr);
>  
>      if (kvm_enabled()) {
> @@ -3733,6 +3738,108 @@ out:
>      error_propagate(errp, local_err);
>  }
>  
> +int spapr_dt_phb(DeviceState *dev, sPAPRMachineState *spapr, void *fdt,
> +                 int *fdt_start_offset, Error **errp)
> +{
> +    sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
> +    uint32_t intc_phandle;
> +
> +    if (spapr_irq_get_phandle(spapr, spapr->fdt_blob, &intc_phandle, errp)) {
> +        return -1;
> +    }
> +
> +    if (spapr_populate_pci_dt(sphb, intc_phandle, fdt, spapr->irq->nr_msis,
> +                              fdt_start_offset)) {
> +        error_setg(errp, "unable to create FDT node for PHB %d", 
> sphb->index);
> +        return -1;
> +    }
> +
> +    /* generally SLOF creates these, for hotplug it's up to QEMU */
> +    _FDT(fdt_setprop_string(fdt, *fdt_start_offset, "name", "pci"));
> +
> +    return 0;
> +}
> +
> +static void spapr_phb_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
> +                               Error **errp)
> +{
> +    sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
> +    sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
> +    sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
> +    const unsigned windows_supported = spapr_phb_windows_supported(sphb);
> +
> +    if (sphb->index == (uint32_t)-1) {
> +        error_setg(errp, "\"index\" for PAPR PHB is mandatory");
> +        return;
> +    }
> +
> +    /*
> +     * This will check that sphb->index doesn't exceed the maximum number of
> +     * PHBs for the current machine type.
> +     */
> +    smc->phb_placement(spapr, sphb->index,
> +                       &sphb->buid, &sphb->io_win_addr,
> +                       &sphb->mem_win_addr, &sphb->mem64_win_addr,
> +                       windows_supported, sphb->dma_liobn, errp);
> +}
> +
> +static void spapr_phb_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
> +                           Error **errp)
> +{
> +    sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
> +    sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
> +    sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
> +    sPAPRDRConnector *drc;
> +    bool hotplugged = spapr_drc_hotplugged(dev);
> +    Error *local_err = NULL;
> +
> +    if (!smc->dr_phb_enabled) {
> +        return;
> +    }
> +
> +    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, sphb->index);
> +    /* hotplug hooks should check it's enabled before getting this far */
> +    assert(drc);
> +
> +    /*
> +     * The FDT fragment will be added during the first invocation of RTAS
> +     * ibm,client-architecture-support  for this device, when we're sure
> +     * that the IOMMU is configured and that QEMU knows the phandle of the
> +     * interrupt controller.
> +     */
> +    spapr_drc_attach(drc, DEVICE(dev), NULL, 0, &local_err);
> +    if (local_err) {
> +        error_propagate(errp, local_err);
> +        return;
> +    }
> +
> +    if (hotplugged) {
> +        spapr_hotplug_req_add_by_index(drc);
> +    } else {
> +        spapr_drc_reset(drc);
> +    }
> +}
> +
> +void spapr_phb_release(DeviceState *dev)
> +{
> +    object_unparent(OBJECT(dev));
> +}
> +

Please call the unplug handler here just like we already do with
spapr_phb_remove_pci_device_cb().

And add a _unplug handler that simply calls e.g.

qdev_simple_device_unplug_cb


Otherwise this will break with
[PATCH RFCv2 0/9] qdev: Hotplug handler chaining + virtio-pmem


> +static void spapr_phb_unplug_request(HotplugHandler *hotplug_dev,
> +                                     DeviceState *dev, Error **errp)
> +{
> +    sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev);
> +    sPAPRDRConnector *drc;
> +
> +    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, sphb->index);
> +    assert(drc);
> +
> +    if (!spapr_drc_unplug_requested(drc)) {
> +        spapr_drc_detach(drc);
> +        spapr_hotplug_req_remove_by_index(drc);
> +    }
> +}
> +
>  static void spapr_machine_device_plug(HotplugHandler *hotplug_dev,
>                                        DeviceState *dev, Error **errp)
>  {
> @@ -3740,6 +3847,8 @@ static void spapr_machine_device_plug(HotplugHandler 
> *hotplug_dev,
>          spapr_memory_plug(hotplug_dev, dev, errp);
>      } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
>          spapr_core_plug(hotplug_dev, dev, errp);
> +    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) 
> {
> +        spapr_phb_plug(hotplug_dev, dev, errp);
>      }
>  }
>  
> @@ -3758,6 +3867,7 @@ static void 
> spapr_machine_device_unplug_request(HotplugHandler *hotplug_dev,
>  {
>      sPAPRMachineState *sms = SPAPR_MACHINE(OBJECT(hotplug_dev));
>      MachineClass *mc = MACHINE_GET_CLASS(sms);
> +    sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
>  
>      if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
>          if (spapr_ovec_test(sms->ov5_cas, OV5_HP_EVT)) {
> @@ -3777,6 +3887,12 @@ static void 
> spapr_machine_device_unplug_request(HotplugHandler *hotplug_dev,
>              return;
>          }
>          spapr_core_unplug_request(hotplug_dev, dev, errp);
> +    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) 
> {
> +        if (!smc->dr_phb_enabled) {
> +            error_setg(errp, "PHB hot unplug not supported on this machine");
> +            return;
> +        }
> +        spapr_phb_unplug_request(hotplug_dev, dev, errp);
>      }
>  }
>  
> @@ -3787,6 +3903,8 @@ static void 
> spapr_machine_device_pre_plug(HotplugHandler *hotplug_dev,
>          spapr_memory_pre_plug(hotplug_dev, dev, errp);
>      } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
>          spapr_core_pre_plug(hotplug_dev, dev, errp);
> +    } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) 
> {
> +        spapr_phb_pre_plug(hotplug_dev, dev, errp);
>      }
>  }
>  
> @@ -3794,7 +3912,8 @@ static HotplugHandler 
> *spapr_get_hotplug_handler(MachineState *machine,
>                                                   DeviceState *dev)
>  {
>      if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) ||
> -        object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
> +        object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE) ||
> +        object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) {
>          return HOTPLUG_HANDLER(machine);
>      }
>      return NULL;
> diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c
> index c5a281915665..22563a381a37 100644
> --- a/hw/ppc/spapr_drc.c
> +++ b/hw/ppc/spapr_drc.c
> @@ -709,6 +709,8 @@ static void spapr_drc_phb_class_init(ObjectClass *k, void 
> *data)
>      drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_PHB;
>      drck->typename = "PHB";
>      drck->drc_name_prefix = "PHB ";
> +    drck->release = spapr_phb_release;
> +    drck->populate_dt = spapr_dt_phb;
>  }
>  
>  static const TypeInfo spapr_dr_connector_info = {
> diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
> index 7df7f6502f93..d0caca627455 100644
> --- a/hw/ppc/spapr_pci.c
> +++ b/hw/ppc/spapr_pci.c
> @@ -1647,21 +1647,7 @@ static void spapr_phb_realize(DeviceState *dev, Error 
> **errp)
>          return;
>      }
>  
> -    if (sphb->index != (uint32_t)-1) {
> -        Error *local_err = NULL;
> -
> -        smc->phb_placement(spapr, sphb->index,
> -                           &sphb->buid, &sphb->io_win_addr,
> -                           &sphb->mem_win_addr, &sphb->mem64_win_addr,
> -                           windows_supported, sphb->dma_liobn, &local_err);
> -        if (local_err) {
> -            error_propagate(errp, local_err);
> -            return;
> -        }
> -    } else {
> -        error_setg(errp, "\"index\" for PAPR PHB is mandatory");
> -        return;
> -    }
> +    assert(sphb->index != (uint32_t)-1); /* checked in spapr_phb_pre_plug() 
> */
>  
>      if (sphb->mem64_win_size != 0) {
>          if (sphb->mem_win_size > SPAPR_PCI_MEM32_WIN_SIZE) {
> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
> index a3074e7fea37..69d9c2196ca2 100644
> --- a/include/hw/ppc/spapr.h
> +++ b/include/hw/ppc/spapr.h
> @@ -764,9 +764,12 @@ void spapr_reallocate_hpt(sPAPRMachineState *spapr, int 
> shift,
>  void spapr_clear_pending_events(sPAPRMachineState *spapr);
>  int spapr_max_server_number(sPAPRMachineState *spapr);
>  
> -/* CPU and LMB DRC release callbacks. */
> +/* DRC callbacks. */
>  void spapr_core_release(DeviceState *dev);
>  void spapr_lmb_release(DeviceState *dev);
> +void spapr_phb_release(DeviceState *dev);
> +int spapr_dt_phb(DeviceState *dev, sPAPRMachineState *spapr, void *fdt,
> +                 int *fdt_start_offset, Error **errp);
>  
>  void spapr_rtc_read(sPAPRRTCState *rtc, struct tm *tm, uint32_t *ns);
>  int spapr_rtc_import_offset(sPAPRRTCState *rtc, int64_t legacy_offset);
> 


-- 

Thanks,

David / dhildenb