[5/5] spapr.c: send QAPI event when memory hotunplug fails

Recent changes allowed the pSeries machine to rollback the hotunplug
process for the DIMM when the guest kernel signals, via a
reconfiguration of the DR connector, that it's not going to release the
LMBs.

Let's also warn QAPI listerners about it. One place to do it would be
right after the unplug state is cleaned up,
spapr_clear_pending_dimm_unplug_state(). This would mean that the
function is now doing more than cleaning up the pending dimm state
though.

This patch does the following changes in spapr.c:

- send a QAPI event to inform that we experienced a failure in the
  hotunplug of the DIMM;

- rename spapr_clear_pending_dimm_unplug_state() to
  spapr_memory_unplug_rollback(). This is a better fit for what the
  function is now doing, and it makes callers care more about what the
  function goal is and less about spapr.c internals such as clearing
  the pending dimm unplug state.

Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
---
 hw/ppc/spapr.c         | 13 +++++++++++--
 hw/ppc/spapr_drc.c     |  5 ++---
 include/hw/ppc/spapr.h |  3 +--
 3 files changed, 14 insertions(+), 7 deletions(-)

On Fri, 26 Feb 2021 13:33:01 -0300
Daniel Henrique Barboza <danielhb413@gmail.com> wrote:

> Recent changes allowed the pSeries machine to rollback the hotunplug
> process for the DIMM when the guest kernel signals, via a
> reconfiguration of the DR connector, that it's not going to release the
> LMBs.
> 
> Let's also warn QAPI listerners about it. One place to do it would be
> right after the unplug state is cleaned up,
> spapr_clear_pending_dimm_unplug_state(). This would mean that the
> function is now doing more than cleaning up the pending dimm state
> though.
> 
> This patch does the following changes in spapr.c:
> 
> - send a QAPI event to inform that we experienced a failure in the
>   hotunplug of the DIMM;
> 
> - rename spapr_clear_pending_dimm_unplug_state() to
>   spapr_memory_unplug_rollback(). This is a better fit for what the
>   function is now doing, and it makes callers care more about what the
>   function goal is and less about spapr.c internals such as clearing
>   the pending dimm unplug state.
> 
> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
> ---

LGTM

Reviewed-by: Greg Kurz <groug@kaod.org>

>  hw/ppc/spapr.c         | 13 +++++++++++--
>  hw/ppc/spapr_drc.c     |  5 ++---
>  include/hw/ppc/spapr.h |  3 +--
>  3 files changed, 14 insertions(+), 7 deletions(-)
> 
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index 6ef72ee7bd..cbe5cafb14 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -28,6 +28,7 @@
>  #include "qemu-common.h"
>  #include "qemu/datadir.h"
>  #include "qapi/error.h"
> +#include "qapi/qapi-events-machine.h"
>  #include "qapi/visitor.h"
>  #include "sysemu/sysemu.h"
>  #include "sysemu/hostmem.h"
> @@ -3575,14 +3576,14 @@ static SpaprDimmState *spapr_recover_pending_dimm_state(SpaprMachineState *ms,
>      return spapr_pending_dimm_unplugs_add(ms, avail_lmbs, dimm);
>  }
>  
> -void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
> -                                           DeviceState *dev)
> +void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev)
>  {
>      SpaprDimmState *ds;
>      PCDIMMDevice *dimm;
>      SpaprDrc *drc;
>      uint32_t nr_lmbs;
>      uint64_t size, addr_start, addr;
> +    g_autofree char *qapi_error = NULL;
>      int i;
>  
>      if (!dev) {
> @@ -3616,6 +3617,14 @@ void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
>          drc->unplug_requested = false;
>          addr += SPAPR_MEMORY_BLOCK_SIZE;
>      }
> +
> +    /*
> +     * Tell QAPI that something happened and the memory
> +     * hotunplug wasn't successful.
> +     */
> +    qapi_error = g_strdup_printf("Memory hotunplug failed for device %s",
> +                                 dev->id);
> +    qapi_event_send_mem_unplug_error(dev->id, qapi_error);
>  }
>  
>  /* Callback to be called during DRC release. */
> diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c
> index 8c4997d795..8faaf9f1dd 100644
> --- a/hw/ppc/spapr_drc.c
> +++ b/hw/ppc/spapr_drc.c
> @@ -1232,12 +1232,11 @@ static void rtas_ibm_configure_connector(PowerPCCPU *cpu,
>  
>      /*
>       * This indicates that the kernel is reconfiguring a LMB due to
> -     * a failed hotunplug. Clear the pending unplug state for the whole
> -     * DIMM.
> +     * a failed hotunplug. Rollback the DIMM unplug process.
>       */
>      if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB &&
>          drc->unplug_requested) {
> -        spapr_clear_pending_dimm_unplug_state(spapr, drc->dev);
> +        spapr_memory_unplug_rollback(spapr, drc->dev);
>      }
>  
>      if (!drc->fdt) {
> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
> index d6edeaaaff..47cebaf3ac 100644
> --- a/include/hw/ppc/spapr.h
> +++ b/include/hw/ppc/spapr.h
> @@ -847,8 +847,7 @@ int spapr_hpt_shift_for_ramsize(uint64_t ramsize);
>  int spapr_reallocate_hpt(SpaprMachineState *spapr, int shift, Error **errp);
>  void spapr_clear_pending_events(SpaprMachineState *spapr);
>  void spapr_clear_pending_hotplug_events(SpaprMachineState *spapr);
> -void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
> -                                           DeviceState *dev);
> +void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev);
>  int spapr_max_server_number(SpaprMachineState *spapr);
>  void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex,
>                        uint64_t pte0, uint64_t pte1);

On Fri, Feb 26, 2021 at 01:33:01PM -0300, Daniel Henrique Barboza wrote:
> Recent changes allowed the pSeries machine to rollback the hotunplug
> process for the DIMM when the guest kernel signals, via a
> reconfiguration of the DR connector, that it's not going to release the
> LMBs.
> 
> Let's also warn QAPI listerners about it. One place to do it would be
> right after the unplug state is cleaned up,
> spapr_clear_pending_dimm_unplug_state(). This would mean that the
> function is now doing more than cleaning up the pending dimm state
> though.
> 
> This patch does the following changes in spapr.c:
> 
> - send a QAPI event to inform that we experienced a failure in the
>   hotunplug of the DIMM;
> 
> - rename spapr_clear_pending_dimm_unplug_state() to
>   spapr_memory_unplug_rollback(). This is a better fit for what the
>   function is now doing, and it makes callers care more about what the
>   function goal is and less about spapr.c internals such as clearing
>   the pending dimm unplug state.
> 
> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
> ---
>  hw/ppc/spapr.c         | 13 +++++++++++--
>  hw/ppc/spapr_drc.c     |  5 ++---
>  include/hw/ppc/spapr.h |  3 +--
>  3 files changed, 14 insertions(+), 7 deletions(-)
> 
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index 6ef72ee7bd..cbe5cafb14 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -28,6 +28,7 @@
>  #include "qemu-common.h"
>  #include "qemu/datadir.h"
>  #include "qapi/error.h"
> +#include "qapi/qapi-events-machine.h"
>  #include "qapi/visitor.h"
>  #include "sysemu/sysemu.h"
>  #include "sysemu/hostmem.h"
> @@ -3575,14 +3576,14 @@ static SpaprDimmState *spapr_recover_pending_dimm_state(SpaprMachineState *ms,
>      return spapr_pending_dimm_unplugs_add(ms, avail_lmbs, dimm);
>  }
>  
> -void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
> -                                           DeviceState *dev)
> +void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev)
>  {
>      SpaprDimmState *ds;
>      PCDIMMDevice *dimm;
>      SpaprDrc *drc;
>      uint32_t nr_lmbs;
>      uint64_t size, addr_start, addr;
> +    g_autofree char *qapi_error = NULL;
>      int i;
>  
>      if (!dev) {
> @@ -3616,6 +3617,14 @@ void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
>          drc->unplug_requested = false;
>          addr += SPAPR_MEMORY_BLOCK_SIZE;
>      }
> +
> +    /*
> +     * Tell QAPI that something happened and the memory
> +     * hotunplug wasn't successful.
> +     */
> +    qapi_error = g_strdup_printf("Memory hotunplug failed for device %s",
> +                                 dev->id);

Might be worth adjusting the error message to make it clearer that it
was the guest which specifically rejected the unplug.  Other than
that, LGTM.

> +    qapi_event_send_mem_unplug_error(dev->id, qapi_error);
>  }
>  
>  /* Callback to be called during DRC release. */
> diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c
> index 8c4997d795..8faaf9f1dd 100644
> --- a/hw/ppc/spapr_drc.c
> +++ b/hw/ppc/spapr_drc.c
> @@ -1232,12 +1232,11 @@ static void rtas_ibm_configure_connector(PowerPCCPU *cpu,
>  
>      /*
>       * This indicates that the kernel is reconfiguring a LMB due to
> -     * a failed hotunplug. Clear the pending unplug state for the whole
> -     * DIMM.
> +     * a failed hotunplug. Rollback the DIMM unplug process.
>       */
>      if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB &&
>          drc->unplug_requested) {
> -        spapr_clear_pending_dimm_unplug_state(spapr, drc->dev);
> +        spapr_memory_unplug_rollback(spapr, drc->dev);
>      }
>  
>      if (!drc->fdt) {
> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
> index d6edeaaaff..47cebaf3ac 100644
> --- a/include/hw/ppc/spapr.h
> +++ b/include/hw/ppc/spapr.h
> @@ -847,8 +847,7 @@ int spapr_hpt_shift_for_ramsize(uint64_t ramsize);
>  int spapr_reallocate_hpt(SpaprMachineState *spapr, int shift, Error **errp);
>  void spapr_clear_pending_events(SpaprMachineState *spapr);
>  void spapr_clear_pending_hotplug_events(SpaprMachineState *spapr);
> -void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
> -                                           DeviceState *dev);
> +void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev);
>  int spapr_max_server_number(SpaprMachineState *spapr);
>  void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex,
>                        uint64_t pte0, uint64_t pte1);